Publications | Jinhu Wang

2026

Cross-platform forest understanding: A multi-platform synergistic training framework for generalized forest point cloud segmentation

Jundi Jiang, Yueqian Shen, Jinhu Wang, W. Daniel Kissling, Markus Hollaus, Hongjun Su, Jinguo Wang, Vagner Ferreira, Norbert Pfeifer

Remote Sensing of Environment 2026

Abs Bib HTML PDF Code

Precise forest inventories are fundamental for sustainable ecosystem management, biodiversity conservation, and assessment of forest carbon stocks. Light Detection and Ranging (LiDAR) has emerged as a dominant remote sensing technique capable of accurately characterizing the vertical canopy profile over large areas. While the growing availability of LiDAR datasets from diverse acquisition platforms has driven significant advances in forest structural component and individual tree segmentation tasks, inherent heterogeneity in data characteristics across multiple platforms poses a critical challenge for cross-platform generalization. Traditional data-driven algorithms often fail to generalize across multi-platform forest datasets due to substantial heterogeneity in data characteristics from different acquisition platforms. Furthermore, conventional multi-platform mixed training strategies induce negative transfer, ultimately undermining segmentation performance. To address the inherent heterogeneity and negative transfer challenges arising from multi-platform datasets, we introduce the Multi-platform Synergistic Training (MST) framework, a unified, data- and model-driven representation learning framework. This framework initially pretrains with virtual synthetic forest datasets to extract generalized feature representations, followed by platform-specific fine-tuning utilizing real-world datasets. Extensive experiments were conducted to evaluate the proposed MST on semantic and instance segmentation tasks using forest benchmark datasets from multiple platforms. The results reveal that the MST achieves consistently high segmentation performance across multi-platform datasets (from airborne, unmanned aerial vehicle, mobile and terrestrial laser scanning). Additionally, leveraging MST pretraining enables the use of only 20% of labeled real-world data to match the segmentation accuracy achieved by training on fully annotated datasets. The MST framework therefore represents a powerful and effective representation learning framework with the potential to support downstream forest inventory and ecological applications.
@article{RSE_2026, title = {Cross-platform forest understanding: A multi-platform synergistic training framework for generalized forest point cloud segmentation}, journal = {Remote Sensing of Environment}, volume = {342}, pages = {115467}, year = {2026}, issn = {0034-4257}, doi = {https://doi.org/10.1016/j.rse.2026.115467}, url = {https://www.sciencedirect.com/science/article/pii/S0034425726002373}, author = {Jundi Jiang and Yueqian Shen and Jinhu Wang and W. Daniel Kissling and Markus Hollaus and Hongjun Su and Jinguo Wang and Vagner Ferreira and Norbert Pfeifer}, keywords = {Forest scene, Semantic segmentation, Instance segmentation, Cross-platform, Negative transfer, Point cloud} }
D4.10 Demonstrator pipeline for habitat condition metric extraction and parallel and distributed computing in a cloud environment

W. Daniel Kissling, Jinhu Wang, and Yifang Shi

ARPHA Preprints 2026

Abs Bib HTML PDF

This deliverable, D4.10 – Demonstrator pipeline for habitat condition metric extraction and parallel and distributed computing in a cloud environment, is produced in the context of the project MAMBO (Modern Approaches to the Monitoring of BiOdiversity), funded by the European Commission through an EU Horizon Europe Research and Innovation Action (Grant Agreement No. 101060639).
@article{Kissling2026, title = {D4.10 Demonstrator pipeline for habitat condition metric extraction and parallel and distributed computing in a cloud environment}, author = {Kissling, W. Daniel and Wang, Jinhu and Shi, Yifang}, journal = {ARPHA Preprints}, year = {2026}, doi = {10.3897/arphapreprints.e190520}, url = {https://preprints.arphahub.com/article/190520/}, }
D6.2 Geospatial data products of habitat metrics derived from LiDAR point clouds at national scales for multiple countries and time periods, findable and accessible through data portals, relevant catalogues or digital repositories

W. Daniel Kissling and Jinhu Wang

ARPHA Preprints 2026

Abs Bib HTML PDF

This document is a data deliverable (D6.2) prepared for the Modern Approaches to the Monitoring of BiOdiversity (MAMBO) project, funded by the European Commission through an EU Horizon Europe Research and Innovation Action (Grant Agreement No. 101060639). The MAMBO project aims to support EU biodiversity policy and address key knowledge gaps by developing and applying innovative tools, workflows, and data products for biodiversity monitoring at multiple spatial and temporal scales. Deliverable D6.2 documents the geospatial research data products of vegetation structure metrics derived from airborne Light Detection and Ranging (LiDAR) point clouds that have been generated within the MAMBO project. The deliverable is of type ‘DATA’ and focuses on the actual datasets produced or collected during the project, rather than on the analysis or interpretation of scientific results. Its primary purpose is to support the principles of Findability, Accessibility, Interoperability, and Reusability (FAIR) by providing a structured overview of the datasets, their scope, and the platforms through which they are made publicly available.
@article{Kissling2026b, title = {D6.2 Geospatial data products of habitat metrics derived from LiDAR point clouds at national scales for multiple countries and time periods, findable and accessible through data portals, relevant catalogues or digital repositories}, author = {Kissling, W. Daniel and Wang, Jinhu}, journal = {ARPHA Preprints}, year = {2026}, doi = {10.3897/arphapreprints.e188540}, url = {https://preprints.arphahub.com/article/188540/}, }

2025

A multi-scale geometric feature-adaptive density-aware framework for robust sub-conductor segmentation in high-voltage transmission corridors

Yueqian Shen, Chenyang Zhang, Jinhu Wang, Jinguo Wang, Junjun Huang, and Yanming Chen

Advances in Space Research 2025

Abs Bib HTML PDF

Fine segmentation of sub-conductors plays a critical role in enabling precise condition assessment for high-voltage transmission corridor inspections. With the widespread applications of bundle conductors in modern power grids, Unmanned Aerial Vehicle Light Detection and Ranging (UAV LiDAR) systems have become indispensable for acquiring sub-conductor point clouds, valued for their operational efficiency and measurement accuracy. However, achieving accurate segmentation in complex power scene point clouds remains challenges due to severe noise interference, high feature similarity among targets, minimal spacing between sub-conductor, and uneven point cloud distribution. To overcome these limitations, this study proposes a novel sub-conductor segmentation algorithm with three core innovations. Firstly, an adaptive multi-scale geometric feature descriptor is designed for the linear span-direction distribution of transmission lines to capture candidate points while mitigating noise interference. Secondly, non-linear mapping strategy using spatial geometric regularities across conductor configurations to reduce dimensionality. Thirdly, an adaptive multi-density perception algorithm is proposed to resolve point cloud density heterogeneity for precise segmentation. Validated across diverse terrains, conductor types, and noise levels, the method achieves an average precision, recall, and F1-score all exceeding 95 %. These results demonstrate its significant potential to advance intelligent inspection capabilities and enhance management efficiency for high-voltage transmission corridors.
@article{shen2025multi, title={A multi-scale geometric feature-adaptive density-aware framework for robust sub-conductor segmentation in high-voltage transmission corridors}, author={Shen, Yueqian and Zhang, Chenyang and Wang, Jinhu and Wang, Jinguo and Huang, Junjun and Chen, Yanming}, journal={Advances in Space Research}, year={2025}, publisher={Elsevier} }
Boosted bagging: A hybrid ensemble deep learning framework for point cloud semantic segmentation of shield tunnel leakage

Jundi Jiang, Yueqian Shen, Jinhu Wang, Yufu Zang, Weitong Wu, Jinguo Wang, Junxi Li, and Vagner Ferreira

Tunnelling and Underground Space Technology 2025

Abs Bib HTML PDF

Accurate leakage detection in subway shield tunnels remains challenging due to the complex geometry and subtle moisture signatures in structural point clouds. Single-model architectures present limited adaptability to heterogeneous leakage and different tunnel scenarios, leading to substantial performance and compromised generalization capacity. To address these challenges, this research proposes Boosted Bagging, a hybrid ensemble deep learning framework for precise semantic segmentation of leakage in tunnel point clouds. In this method, we propose a boosted learner that integrates three specialized base classifiers to learn complex feature representations of diverse leakage patterns. The boosted learner further synergizes with the bagging strategy to enhance generalization capacity by parallel training on randomized data subsets and voting strategy. Integrating boosting and bagging strategies results in a more precise and robust tunnel leakage segmentation. Moreover, the Lovasz Hinge Loss is introduced to address severe sample imbalance between the leakage and background classes. The experimental results demonstrate the effectiveness of Boosted Bagging in terms of segmentation accuracy and robustness. Comparative experiments with state-of-the-art segmentation methods reveal a notable enhancement in segmentation accuracy. Moreover, its superior performance on test datasets highlights the strong generalization capability of the method.
@article{jiang2025boosted, title={Boosted bagging: A hybrid ensemble deep learning framework for point cloud semantic segmentation of shield tunnel leakage}, author={Jiang, Jundi and Shen, Yueqian and Wang, Jinhu and Zang, Yufu and Wu, Weitong and Wang, Jinguo and Li, Junxi and Ferreira, Vagner}, journal={Tunnelling and Underground Space Technology}, year={2025}, publisher={Elsevier} }
AdLeaf: Quantitative leaf reconstruction from TLS point clouds

Guangpeng Fan, Liangliang Xu, Jiani Guo, Ruoyoulan Wang, Haoran Zhao, Hao Lu, Jinhu Wang, Di Wang, Feixiang Chen, and Liangliang Nan

IEEE Transactions on Geoscience and Remote Sensing 2025

Abs Bib HTML PDF

Quantitatively reconstructing the 3-D structure of individual leaves within tree canopies is critical for understanding forest function and environmental responses to climate change. While quantitative structure models (QSMs) using terrestrial laser scanning (TLS) effectively capture woody structures, they lack the capability to accurately reconstruct nonwoody leaf components. This study proposes accurate and detailed leaf (AdLeaf), a novel approach for fine-scale reconstruction of individual leaves using TLS point clouds. AdLeaf combines wood–leaf separation, individual leaf segmentation, detection and repair of incomplete leaves, explicit reconstruction, and parameter extraction. It automates semantic segmentation at the tree scale to separate woody and leafy components. Instance segmentation is refined through similarity graphs. Incomplete leaves are detected and repaired using shape concavity analysis and symmetry-based mirroring. AdLeaf enables direct measurement of leaf attributes, including count, area, inclination, volume, and azimuth. Validation using field scans, synthetic data, and both in situ and destructive measurements shows high accuracy: leaf counting errors ranged from 0.58% to 8.23% for trees with 201–4000 leaves. Reconstructed leaf geometries had mean and standard deviations (SDs) below 0.83 and 0.70 cm, respectively. Leaf area measurements (10–180 cm2) achieved a coefficient of determination (R2) of 0.95, a bias of −0.20 cm2, and a root-mean-square error of 5.63 cm2. Incomplete leaf detection errors were below 28%, with the repaired area relative root-mean-square error (rRMSE) reduced by 9.4%. By addressing QSM limitations, AdLeaf enables explicit 3-D leaf reconstructions that support detailed analysis of canopy light interception, spatial heterogeneity, and photosynthesis. It provides a robust framework for linking leaf structure to function at the tree level, advancing forest structure and radiative transfer research.
@article{fan2025adleaf, title={AdLeaf: Quantitative leaf reconstruction from TLS point clouds}, author={Fan, Guangpeng and Xu, Liangliang and Guo, Jiani and Wang, Ruoyoulan and Zhao, Haoran and Lu, Hao and Wang, Jinhu and Wang, Di and Chen, Feixiang and Nan, Liangliang}, journal={IEEE Transactions on Geoscience and Remote Sensing}, year={2025}, publisher={IEEE} }
Advances and challenges in water leakage detection techniques for shield tunnels: A comprehensive review

Jundi Jiang, Yueqian Shen, Jinhu Wang, Jinguo Wang, Junjun Huang, Sshihan Fu, Kai Guo, and Vagner Ferreira

Measurement 2025

Abs Bib HTML PDF Data

Water leakage in shield tunnels presents significant challenges to the long-term stability and safety of underground infrastructure, making its effective detection imperative. In this context, data acquisition methods, including LiDAR (Light Detection and Ranging), photogrammetry, and thermal infrared imaging, have emerged as effective non-contact techniques for identifying water leakage. These modern sensing techniques offer substantial advantages over traditional manual inspection methods. However, the inherent characteristics of these sensors introduce specific challenges for water leakage detection, which hinder its effectiveness of tunnel and practical applications. This review examines recent methodologies designed to overcome these obstacles. It begins with an exploration of the three primary sensors utilized in tunnel water leakage detection. Then, representative techniques corresponding to each sensor are described, highlighting their potential and limitations, and qualitative analyses are incorporated to enhance understanding. To further address the lack of publicly available datasets, this review presents a novel LiDAR-acquired point cloud dataset specifically developed for tunnel water leakage detection, in addition to discussing existing photogrammetry-based datasets. The developed dataset comprises 4427 annotated leakage instances, totaling 22.71 million points, with an average point spacing of 2.1 mm. To the best of our knowledge, this is the first comprehensive review of tunnel water leakage detection and the first publicly available point cloud dataset dedicated to this task. This review provide an exhaustive analysis and discussion of the multifaceted aspects of tunnel water leakage detection, thereby assisting researchers in advancing the field and developing more effective detection and maintenance strategies.
@article{jiang2025advances, title={Advances and challenges in water leakage detection techniques for shield tunnels: A comprehensive review}, author={Jiang, Jundi and Shen, Yueqian and Wang, Jinhu and Wang, Jinguo and Huang, Junjun and Fu, Sshihan and Guo, Kai and Ferreira, Vagner}, journal={Measurement}, year={2025}, publisher={Elsevier} }
A workflow for extracting ungulate trails in wetlands using 3D point clouds obtained from airborne laser scanning

Jinhu Wang, Perry Cornelissen, and W. Daniel Kissling

Frontiers in Remote Sensing 2025

Abs Bib HTML PDF Data Code

Ungulates and other mammalian herbivores can create trails in dense vegetation by trampling and browsing. This can affect vegetation structure and result in the fragmentation of closed, high vegetation, with subsequent impacts on biodiversity. Manually mapping trails in the field or from aerial photographs can be challenging and time-consuming, especially in inaccessible or difficult-to-access habitats such as wetlands and if trails occur beneath the canopy of woody plants (i.e., trees and shrubs) or in other tall vegetation (e.g., reed). Airborne laser scanning (ALS) provides an alternative method because Light Detection and Ranging (LiDAR) can record returns from both the canopy and the ground, as some laser pulses pass through gaps in the vegetation, resulting in highly accurate and dense three-dimensional (3D) point clouds. Here, we present a workflow for extracting ungulate trails using 3D point clouds obtained from country-wide ALS surveys, illustrated by red deer trampling in reedbeds within a 36 km2 marsh area of a Dutch nature reserve. The workflow starts by pre-processing to retile the LiDAR point clouds to designated tiles and removes outliers from the raw data. The (near-)terrain points are then segmented using an iterative filtering algorithm, and digital terrain models are generated with a user-defined resolution. Finally, trail cells are extracted by thresholding the residuals from iterative Laplacian smoothing and then refined by sparse 3D structure tensor voting. The parameters of the workflow were optimized with comprehensive sensitivity analyses. Applying the workflow resulted in a classification of trail and non-trail grid cells at 10 cm resolution across the study area. Compared to manually labeled ground truths, the results showed an overall accuracy of 93% and 90% in regions of red deer grazing only and both geese and red deer grazing, respectively. To test its transferability, the workflow could be applied to other LiDAR data (e.g., ALS surveys from another flight campaign in the same study area or in a different country), to other nature areas (e.g., other rewilding sites or other wetlands), and to other ungulate species (e.g., domesticated livestock or other native large herbivores).
@article{wang2025workflow, title={A workflow for extracting ungulate trails in wetlands using 3D point clouds obtained from airborne laser scanning}, author={Wang, Jinhu and Cornelissen, Perry and Kissling, W. Daniel}, journal={Frontiers in Remote Sensing}, year={2025}, publisher={Frontiers} }
Multi-temporal high-resolution data products of ecosystem structure derived from country-wide airborne laser scanning surveys of the Netherlands

Yifang Shi, Jinhu Wang, and W. Daniel Kissling

Earth System Science Data 2025

Abs Bib HTML PDF Data

Recent years have seen a rapid surge in the use of light detection and ranging (lidar) technology for characterizing the structure of ecosystems. Even though repeated airborne laser scanning (ALS) surveys are becoming increasingly available across several European countries, so far, only a few studies have derived data products of ecosystem structure at a national scale, possibly due to a lack of free and open-source tools and the computational challenges involved in handling the large volumes of data. Nevertheless, high-resolution data products of ecosystem structure generated from multi-temporal country-wide ALS datasets are urgently needed if we are to integrate such information into biodiversity and ecosystem science. By employing a recently developed, open-source, high-throughput workflow (named “Laserfarm”), we processed around 70 TB of raw point clouds collected from four national ALS surveys of the Netherlands (AHN1–AHN4, 1996–2022). This resulted in ∼59 GB raster layers in GeoTIFF format constituting ready-to-use multi-temporal data products of ecosystem structure at a national scale. For each AHN (Actueel Hoogtebestand Nederland) dataset, we generated 25 lidar-derived vegetation metrics at 10 m spatial resolution, representing vegetation height, vegetation cover, and vegetation structural variability, together with auxiliary data (∼12 GB) such as raster layers of point density; pulse density; flight line timestamp information; terrain and surface elevation; and masks of water areas, roads, buildings, power lines, and NA values (areas with no points available). The data enable an in-depth understanding of ecosystem structure at a fine resolution across the Netherlands and provide opportunities for exploring ecosystem structural dynamics over time. To illustrate the utility of these data products, we present ecological use cases that monitor forest structural change and analyse vegetation structure differences across various Natura 2000 habitat types, including dunes, marshes, grasslands, shrublands, and woodlands. The provided data products and the employed workflow can facilitate a wide use and uptake of ecosystem structure information in biodiversity and carbon modelling, conservation science, and ecosystem management. The full data products are publicly available on Zenodo (https://doi.org/10.5281/zenodo.13940846, Shi et al., 2025a).
@article{shi2025multi, title={Multi-temporal high-resolution data products of ecosystem structure derived from country-wide airborne laser scanning surveys of the Netherlands}, author={Shi, Yifang and Wang, Jinhu and Kissling, W. Daniel}, journal={Earth System Science Data}, year={2025}, publisher={Copernicus Publications} }
Data of vegetation structure metrics retrieved from airborne laser scanning surveys for European demonstration sites

W. Daniel Kissling, W. Mulder, Jinhu Wang, and Yifang Shi

Data in Brief 2025

Abs Bib HTML PDF Data

This dataset provides a standardized collection of rasterized Light Detection And Ranging (LiDAR) metrics in GeoTIFF format, derived from country-wide airborne laser scanning (ALS) data across seven demonstration sites in five European countries: Mols Bjerge National Park (Denmark), Reserve Naturelle Nationale du Bagnas (France), Oostvaardersplassen (Netherlands), Salisbury Plain (United Kingdom), Knepp Estate (United Kingdom), Monks Wood (United Kingdom), and the island of Comino (Malta). The sites range in areal size from 0.08 km2 to 54 km2 and include habitat types such as forests, broadleaf and conifer woodlands, small plantations, dry and wet grasslands, marshes, reedbeds, arable fields, farmland, scrublands and mediterranean garigue. A total of 35 LiDAR metrics were calculated, of which 28 represent vegetation structural attributes. These include vegetation height (seven metrics), vegetation cover (fourteen metrics), and vegetation vertical variability (seven metrics). Additionally, seven metrics describe point density (one metric), eigenvalues (three metrics), and normal vectors (three metrics). The rasterized LiDAR metrics have a spatial resolution of 10 m, with coverage and extent defined by shapefiles corresponding to each demonstration site. The raw ALS point clouds were clipped to the site boundaries and processed with the 'Laserfarm' workflow, a standardized computational workflow that includes modular pipelines for re-tiling, normalization, feature extraction, and rasterization. Laserfarm employs the feature extraction module of the open-source ‘Laserchicken’ software to compute the LiDAR metrics. The workflow was implemented using the IT services of the Dutch national facility for information and communication technology, SURF. The clipped LiDAR point clouds are available through a public repository, except for the LiDAR point clouds from Comino, Malta, which are not publicly available. The 35 rasterized LiDAR metrics (GeoTIFF files, 10 m resolution) from all sites, including Comino, as well as the corresponding site boundary shapefiles (geospatial vector format), are provided in a Zenodo repository. Additionally, the Jupyter Notebooks with Python code for executing the Laserfarm workflow are available to facilitate reproducibility and further computational applications. Users should note that the rasterized LiDAR metrics may contain zero or NA values, particularly over water surfaces, with the pulse penetration ratio metric potentially indicating false high vegetation cover over water. Users may reclassify or mask areas with zero values accordingly. Some pixels exhibit abnormal vegetation height values, which can be filtered before analysis. Certain striping patterns, likely resulting from overlapping flight lines and increased point density, are present in some metrics, though their overall impact appears minimal. This dataset enables diverse applications, including canopy height measurements, mapping of hedgerows, treelines, and forest patches, as well as characterizing vegetation density, vertical stratification, and habitat openness. It supports landscape-scale habitat analysis and contributes to the standardization of vegetation metrics from ALS data for site-specific ecological monitoring (e.g., Natura 2000). Moreover, the dataset demonstrates the automated execution of LiDAR data processing workflows, which is crucial for establishing a transnational and multi-site biodiversity and ecosystem observation network.
@article{kissling2025data, title={Data of vegetation structure metrics retrieved from airborne laser scanning surveys for European demonstration sites}, author={Kissling, W. Daniel and Mulder, Wessel and Wang, Jinhu and Shi, Yifang}, journal={Data in Brief}, year={2025}, publisher={Elsevier} }
GEPT-Net: An efficient geometry enhanced point transformer for shield tunnel leakage segmentation

Jundi Jiang, Yueqian Shen, Jinhu Wang, Jinguo Wang, Chenyang Zhang, Jingyi Wang, and Vagner Ferreira

ISPRS Journal of Photogrammetry and Remote Sensing 2025

Abs Bib HTML PDF Data

Subway shield tunnels have emerged as the preferred solution for urban transportation due to their convenience and safety. Constructed using prefabricated concrete segments, these tunnels exhibit structural stability. However, the segment joints and bolt holes are prone to groundwater infiltration under prolonged external stress, potentially compromising the lifespan of the shield tunnels. Consequently, effective detection methods are imperative to ensure the safe operation of these tunnels. Accurate data acquisition and precise extraction of leakage features are critical for detecting leakages in subway tunnels. This research introduces Efficient Geometry Enhanced Point Transformer Network (GEPT-Net), an innovative point cloud semantic segmentation network designed specifically for detecting tunnel leakage. GEPT-Net leverages the observation that leakages predominantly occur at segment joints and bolt holes, characterized by distinct geometric features and lower intensity. The network incorporates Fast Point Feature Histograms (FPFH) to effectively capture these geometric features from the input data. Additionally, we introduce a point cloud serialization technique utilizing space-filling curves, enabling the network to perceive a greater number of points within the same computational power, thereby balancing efficiency and accuracy. The Geometry Enhanced Channel Attention (GECA) Block is introduced to enhance the interaction between FPFH feature channels and intensity channels, enhancing the precise localization of leakage areas. Furthermore, the Lovasz Hinge Loss is employed to address the issue of extreme class imbalance. We constructed a tunnel leakage point cloud dataset, named S3DIS_leakage, comprising approximately 1,600 m between two stations, to train and evaluate the performance of our network. Experimental results demonstrate that GEPT-Net achieves superior performance in tunnel leakage semantic segmentation, attaining approximately 85 % mean Intersection over Union and 89 % accuracy for leakage classes, outperforming cutting-edge 2D and 3D networks by at least 12 %. Moreover, GEPT-Net maintains a remarkable balance between segmentation accuracy and computational efficiency, rendering it viable for practical engineering applications. This study not only establishes a robust approach for tunnel leakage detection but also paves the way for future research on the comprehensive segmentation of shield tunnel components. The proposed framework is available from the following github repository: https://github.com/jdjiang312/GEPT-Net.
@article{jiang2025gept, title={GEPT-Net: An efficient geometry enhanced point transformer for shield tunnel leakage segmentation}, author={Jiang, Jundi and Shen, Yueqian and Wang, Jinhu and Wang, Jinguo and Zhang, Chenyang and Wang, Jingyi and Ferreira, Vagner}, journal={ISPRS Journal of Photogrammetry and Remote Sensing}, year={2025}, publisher={Elsevier} }

2024

Towards consistently measuring and monitoring habitat condition with airborne laser scanning and unmanned aerial vehicles

W. Daniel Kissling, Yifang Shi, Jinhu Wang, Agata Walicka, Charles George, Jesper E. Moeslund, and France Gerard

Ecological Indicators 2024

Abs Bib HTML PDF Data Code

Indicators of habitat condition are essential for tracking conservation progress, but measuring biotic, abiotic and landscape characteristics at fine resolution over large spatial extents remains challenging. In this viewpoint article, we provide a comprehensive synthesis of the challenges and solutions for consistently measuring and monitoring habitat condition with remote sensing using airborne Light Detection and Ranging (LiDAR) and affordable Unmanned Aerial Vehicles (UAVs) over multiple sites and transnational or continental extents. Key challenges include variability in sensor characteristics and survey designs, non-transparent pre-processing workflows, heterogeneous and complex data, issues with the robustness of metrics and indices, limited model generalizability and transferability across sites, and difficulties in handling big data, such as managing large volumes and utilizing parallel or distributed computing. We suggest that a collaborative cloud virtual research environment (VRE) for habitat condition research and monitoring could provide solutions, including tools for data discovery, access, and data standardization, as well as geospatial processing workflows for airborne LiDAR and UAV data. A VRE would also improve data management, metadata standardization, workflow reproducibility, and transferability of structure-from-motion algorithms and machine learning models such as random forests and convolutional neural networks. Along with best practices for data collection and adopting FAIR (findability, accessibility, interoperability, reusability) principles and open science practices, a VRE could enable more consistent and transparent data processing and metric retrieval, e.g., for Natura 2000 habitats. Ultimately, these improvements would support the development of more reliable habitat condition indicators, helping prevent habitat degradation and promoting the sustainable use of natural resources.
@article{kissling2024towards, title={Towards consistently measuring and monitoring habitat condition with airborne laser scanning and unmanned aerial vehicles}, author={Kissling, W. Daniel and Shi, Yifang and Wang, Jinhu and Walicka, Agata and George, Charles and Moeslund, Jesper E. and Gerard, France}, journal={Ecological Indicators}, year={2024}, publisher={Elsevier} }
Coarse-to-fine separation of wood and leaf from MLS street tree point clouds using branch tilt prior and enhanced shortest path tracing

Yueqian Shen, Shuangshuang Ji, Jinhu Wang, Weidong Liu, Jinguo Wang, Yanming Chen, Zili Deng, Shihan Fu, and Dong Chen

IEEE Transactions on Geoscience and Remote Sensing 2024

Abs Bib HTML PDF

Trees play a crucial role in promoting green, ecological, and low-carbon cities, with street trees being essential for urban roadways. Understanding the 3-D structure and biological characteristics of these trees requires accurate separation of wood and leaf. Mobile laser scanning (MLS) technology, known for its high efficiency and resolution, offers significant advantages. MLS data, however, often contain missing or overlapping areas due to occlusions and scanning geometry, complicating precise urban tree modeling. To address these challenges, this article introduces a coarse-to-fine approach for distinguishing wood from leaves in urban street trees. The proposed method begins with a hierarchical workflow that integrates the density-based spatial clustering of applications with noise (DBSCAN) algorithm to identify individual tree nodes. These nodes form the basis for constructing a graph structure for each tree. By leveraging prior knowledge of branch tilt angles, we enhance the shortest path algorithm, facilitating the extraction of features like shortest path frequency and length. This initial step completes a coarse differentiation between wood and leaves. To further refine accuracy, the identified wood and leaf points undergo analysis to extract multiscale geometric features. Integrating these features with the random forest (RF) algorithm results in a more precise separation of wood and leaf points. Our method demonstrates promising segmentation capabilities in MLS-captured roadside trees. Compared to four state-of-the-art methods for wood and leaf separation, our approach shows superior accuracy and efficiency, particularly in accurately identifying trunk points and minor branch points, as well as classifying the outer canopy layer.
@article{shen2024coarse, title={Coarse-to-fine separation of wood and leaf from MLS street tree point clouds using branch tilt prior and enhanced shortest path tracing}, author={Shen, Yueqian and Ji, Shuangshuang and Wang, Jinhu and Liu, Weidong and Wang, Jinguo and Chen, Yanming and Deng, Zili and Fu, Shihan and Chen, Dong}, journal={IEEE Transactions on Geoscience and Remote Sensing}, year={2024}, publisher={IEEE} }

2022

A Deep Learning Based Method for Railway Overhead Wire Reconstruction from Airborne LiDAR Data

Lele Zhang, Jinhu Wang, Yueqian Shen, Jian Liang, Yuyu Chen, Linsheng Chen, and Mei Zhou

Remote Sensing 2022

Abs Bib HTML PDF Code

Automatically and accurately reconstructing the overhead wires of railway from airborne laser scanning (ALS) data are an efficient way of railway monitoring to ensure stable and safety transportation services. However, due to the complex structure of the overhead wires, it is challenging to extract these wires using the existing methods. This work proposes a workflow for railway overhead wire reconstruction using deep learning for wire identification collaborating with the RANdom SAmple Consensus (RANSAC) algorithm for wire reconstruction. First, data augmentation and ground points down-sampling are performed to facilitate the issues caused by insufficient and non-uniformity of LiDAR points. Then, a network incorporating with PointNet model is proposed to segment wires, pylons and ground points. The proposed network is composed of a Geometry Feature Extraction (GFE) module and a Neighborhood Information Aggregation (NIA) module. These two modules are introduced to encode and describe the local geometric features. Therefore, the capability of the model to discriminate geometric details is enhanced. Finally, a wire individualization and multi-wire fitting algorithm is proposed to reconstruct the overhead wires. A number of experiments are conducted using ALS point cloud data of railway scenarios. The results show that the accuracy and MIoU for wire identification are 96.89% and 82.56%, respectively, which demonstrates a better performance compared to the existing methods. The overall reconstruction accuracy is 96% over the study area. Furthermore, the presented strategy also demonstrated its applicability to high-voltage powerline scenarios.
@article{Zhang2022, author = {Zhang, Lele and Wang, Jinhu and Shen, Yueqian and Liang, Jian and Chen, Yuyu and Chen, Linsheng and Zhou, Mei}, title = {A Deep Learning Based Method for Railway Overhead Wire Reconstruction from Airborne LiDAR Data}, journal = {Remote Sensing}, volume = {14}, year = {2022}, number = {20}, article-number = {5272}, url = {https://www.mdpi.com/2072-4292/14/20/5272}, issn = {2072-4292}, doi = {10.3390/rs14205272}, }
Plot-level reconstruction of 3D tree models for aboveground biomass estimation

Guangpeng Fan, Zhenyu Xu, Jinhu Wang, Liangliang Nan, Huijie Xiao, Zhiming Xin, and Feixiang Chen

Ecological Indicators 2022

Abs Bib HTML PDF

Complexity of forest structure is an important factor contributing to uncertainty in aboveground biomass estimates. In this study, we present a new method for reducing uncertainty in forest aboveground biomass (AGB) estimation based on plot-level terrestrial laser scanner (TLS) point clouds reconstruction. The method estimates the total AGB of plots with complex structures after automatically performing the steps of ground point filtering, single tree segmentation, and three-dimensional (3D) structure reconstruction. We used plot data from temperate and tropical forest ecosystems to verify the effectiveness of the method, reconstructing a 1300 m2 temperate plantation plot and a 5000 m2 mingled forest plot, respectively. The total biomass of 153 trees in the plantation plot was overestimated by 17.12 %, and the total biomass of 61 trees in the mingled forest plot was underestimated by 10.88 %. We found that the uncertainty of aboveground biomass estimation in tropical forests with more complex structures is not necessarily greater than in plantations. Therefore, in large-scale remote sensing observations of forest biomass, the number or area of plots can be increased to reduce the uncertainty of the results caused by the complex structure. The focus of this study is to explore TLS point clouds modeling methods to reduce the uncertainty in AGB estimation caused by the complexity of forest structures, and to provide reference cases for plot-level point clouds reconstruction methods. Forest ecologists can use this method to regularly observe forest growth and obtain indicators related to forest ecology without destroying trees.
@article{Fan2022, title = {Plot-level reconstruction of 3D tree models for aboveground biomass estimation}, journal = {Ecological Indicators}, volume = {142}, pages = {109211}, year = {2022}, issn = {1470-160X}, doi = {https://doi.org/10.1016/j.ecolind.2022.109211}, url = {https://www.sciencedirect.com/science/article/pii/S1470160X22006835}, author = {Fan, Guangpeng and Xu, Zhenyu and Wang, Jinhu and Nan, Liangliang and Xiao, Huijie and Xin, Zhiming and Chen, Feixiang}, keywords = {Complex forest structure, Above-ground biomass, Estimation uncertainty, Plot-level, TLS point clouds}, }
Road marking detection and extraction method based on neighborhood density and Kalman Filter

Xiaoyu Li, Mei Zhou, Jinhu Wang, and Qiangqiang Yao

Journal of University of Chinese Academy of Sciences 2022

Abs Bib HTML

This paper presents a methodology for detection and extraction of road marking based on neighborhood point density and Kalman Filter from mobile laser scanning in three steps: 1) Segmenting road point clouds into scan lines; 2) Generating convolution kernel based on point density in neighborhood for extracting road marking contour points; 3)Fitting contour line using the least squares algorithm and completing omitted road markings using Kalman Filter. A quantitative validation shows that the average deviation of center points and orientation are 0.04 m and 0.04 respectively, and the average completeness of results are 99.69%. The proposed method reduces the influence of unevenly distributed points on road markings extraction and improves the overall extraction completeness.
@article{Li2022, author = {Li, Xiaoyu and Zhou, Mei and Wang, Jinhu and Yao, Qiangqiang}, journal = {Journal of University of Chinese Academy of Sciences}, number = {2}, title = {Road marking detection and extraction method based on neighborhood density and Kalman Filter}, volume = {4}, year = {2022}, doi = {10.7523/j.ucas.2022.024}, }
顾及相对距离的路灯点云分层提取方法研究

马茜芮, 沈月千, Jinhu Wang, and 黄腾

Laser & Optoelectronics Progress 2022

Abs

Street lamp extraction is an important research direction for target extraction from point clouds obtained using vehicle - borne laser scanning. However, the upper and lower parts of street lamps always produce adhesion and occlusion, making street lamp identification difficult. Considering that the adhesion and occlusion are unlikely to occur in the lamp pole’s middle, relative position relationship between lamp burner and lamp pole is examined and a hierarchical extraction approach for street lamp point cloud considering the relative distance is introduced. First, the original point cloud is divided into the lamp burner, lamp pole, and ground layers using the cloth simulation filtering (CSF) algorithm, then the connected component analysis is used to cluster the lamp burner layer and lamp pole layer point clouds. Then, the lamp pole point cloud is extracted using the diagonal’s length in each clustering rectangle of the lamp pole layer and the fitted circle’s included area. Finally, the lamp burner point cloud is estimated based on the relative distance between the lamp burner’s center and the lamp pole’s center to extract the entire street lamp. The proposed method was tested on three datasets. The proposed method’s extracted correctness, completeness, quality, and F1 value for data 1 are 100%; the correctness, completeness, and F1 value for data 2 are 87. 50% while the quality is 77. 78%; the completeness and quality for data 3 are 94. 74%, and the correctness is 100% while the F1 value is 97. 30%. The experimental findings illustrate that this method can efficiently recognize and extract street lamps

2021

Methodology for extraction of tunnel cross-section using dense point cloud data

Yueqian Shen, Jinguo Wang, Jinhu Wang, Wei Duan, and Vagner Ferreira

Journal of Geodesy and Geoinformation Science 2021

Abs Bib

Tunnel deformation monitoring is a crucial task to evaluate tunnel stability during the metro operation period. Terrestrial Laser Scanning (TLS) can collect high density and high accuracy point cloud in a few minutes as an innovation technique, which provides promising applications in tunnel deformation monitoring. Here, an efficient method for extracting tunnel cross-sections and convergence analysis using dense TLS point cloud data is proposed. First, the tunnel orientation is determined using principal component analysis (PCA) in Euclidean plane. Two control points are introduced to detect and remove the unsuitable points by using point cloud division and then the ground points are removed by defining an elevation value width of 0.5 m. Next, a z-score method is introduced to detect and remove outliers. Because the tunnel cross-section’s standard shape is round, the circle fitting is implemented using the least-squares method. Afterward, the convergence analysis is made at the angles of 0, 30 and 150 degrees. The proposed approach’s feasibility is tasted on a TLS point cloud of a Nanjing subway tunnel acquired using a Faro X330 laser scanner. The results indicate that the proposed methodology achieves an overall accuracy of 1.34 mm, which is also in agreement with the measurements acquired by a total station instrument. The proposed methodology provides new insights and references for the application of TLS in tunnel deformation monitoring, which can also be extended to other engineering applications.
@article{Shen2021, author = {Shen, Yueqian and Wang, Jinguo and Wang, Jinhu and Duan, Wei and Ferreira, Vagner}, journal = {Journal of Geodesy and Geoinformation Science}, number = {2}, title = {Methodology for extraction of tunnel cross-section using dense point cloud data}, volume = {4}, year = {2021}, keywords = {cross-section, control point, convergence analysis, z-score method, terrestrial laser scanning, dense point cloiud data}, doi = {10.11947/j.JGGS.2021.0206}, }

2019

Automatic extraction of power lines from UAV LiDAR point clouds using a novel spatial feature

Mei Zhou, Kuangyu Li, Jinhu Wang, Chuanrong Li, Geer Teng, Lian Ma, Haohao Wu, Wei Li, Huijing Zhang, Jiuying Chen, and Linshen Chen

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019

Abs Bib HTML

UAV LiDAR systems have unique advantage in acquiring 3D geo-information of the targets and the expenses are very reasonable; therefore, they are capable of security inspection of high-voltage power lines. There are already several methods for power line extraction from LiDAR point cloud data. However, the existing methods either introduce classification errors during point cloud filtering, or occasionally unable to detect multiple power lines in vertical arrangement. This paper proposes and implements an automatic power line extraction method based on 3D spatial features. Different from the existing power line extraction methods, the proposed method processes the LiDAR point cloud data vertically, therefore, the possible location of the power line in point cloud data can be predicted without filtering. Next, segmentation is conducted on candidates of power line using 3D region growing method. Then, linear point sets are extracted by linear discriminant method in this paper. Finally, power lines are extracted from the candidate linear point sets based on extension and direction features. The effectiveness and feasibility of the proposed method were verified by real data of UAV LiDAR point cloud data in Sichuan, China. The average correct extraction rate of power line points is 98.18%.
@article{Zhou2019b, author = {Zhou, Mei and Li, Kuangyu and Wang, Jinhu and Li, Chuanrong and Teng, Geer and Ma, Lian and Wu, Haohao and Li, Wei and Zhang, Huijing and Chen, Jiuying and Chen, Linshen}, title = {Automatic extraction of power lines from UAV LiDAR point clouds using a novel spatial feature}, journal = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {IV-2/W7}, year = {2019}, pages = {227--234}, url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/227/2019/}, doi = {10.5194/isprs-annals-IV-2-W7-227-2019}, }
Analysis of influencing factors of curve matching based geometric calibration for ZY3-02 altimeter data

Mei Zhou, Linshen Chen, Jinhu Wang, Geer Teng, Chuanrong Li, Qiangqiang Yao, and Jiuying Chen

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019

Abs Bib HTML

High-precision on-orbit geometric calibration of spaceborne laser altimetry data is essential to its effective applications. Firstly, the existing calibration methods for laser altimeter data are analyzed. Then, a geometric calibration method based on curve matching is proposed. Compared to the existing methods, the proposed method does not rely on ground calibration field. Thus, it is efficiency in expense and time. Notably, three factors, i.e. matching method, initial control point selection and the step size of matching step, which significantly affect the results of calibration are analyzed respectively. The analysis was validated based on the original laser altimetry data obtained by ZY3-02 satellite. According to the results, the following conclusions can be drawn preliminarily: (1) Both the correlation coefficient maximum (COR) criterion and the mean square error minimum (MSD) criterion in the curve matching can be used to correct the systematic error in altimetry data. (2) The initial control points of the selected track should have a significant change trend and the slope within the laser footprints should be less than 15°. (3) Current experimental data show that the best step size for matching search is 10 m. The relevant conclusions can provide reference for the research of geometrical calibration and data processing of the same type of laser altimetry satellite.
@article{Zhou2019, author = {Zhou, Mei and Chen, Linshen and Wang, Jinhu and Teng, Geer and Li, Chuanrong and Yao, Qiangqiang and Chen, Jiuying}, title = {Analysis of influencing factors of curve matching based geometric calibration for ZY3-02 altimeter data}, journal = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {IV-2/W7}, year = {2019}, pages = {221--226}, url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/221/2019/}, doi = {10.5194/isprs-annals-IV-2-W7-221-2019}, }

Laser Scanning : An Emerging Technology in Structural Engineering

Roderik Lindenbergh, Sylvie Soudarissanane, Jinhu Wang, Abdul Nurunnabi, Adriaan Natijne, and Cserép Máté

CRC Press (Book Chapter) 2019

Bib HTML

@inbook{Lindenbergh2019,
  author = {Lindenbergh, Roderik and Soudarissanane, Sylvie and Wang, Jinhu and Nurunnabi, Abdul and van Natijne, Adriaan and Máté, Cserép},
  editor = {Riveiro, Belen and Lindenbergh, Roderik},
  chapter = {Laser scanning for operational multiscale structural monitoring},
  pages = {14},
  publisher = {CRC Press},
  title = {Laser Scanning : An Emerging Technology in Structural Engineering},
  year = {2019},
  edition = {1st},
  isbn = {9781351018869},
}

2018

International benchmarking of terrestrial laser scanning approaches for forest inventories

Xinlian Liang, Juha Hyyppä, Harri Kaartinen, Matti Lehtomäki, Jiri Pyörälä, Norbert Pfeifer, Markus Holopainen, Gábor Brolly, Pirotti Francesco, Jan Hackenberg, Huabing Huang, Hyun-Woo Jo, Masato Katoh, Luxia Liu, Martin Mokroš, Jules Morel, Kenneth Olofsson, Jose Poveda-Lopez, Jan Trochta, Di Wang, Jinhu Wang, Zhouxi Xi, Bisheng Yang, Guang Zheng, Ville Kankare, Ville Luoma, Xiaowei Yu, Liang Chen, Mikko Vastaranta, Ninni Saarinen, and Yunsheng Wang

ISPRS Journal of Photogrammetry and Remote Sensing 2018

Abs Bib HTML PDF

The last two decades have witnessed increasing awareness of the potential of terrestrial laser scanning (TLS) in forest applications in both public and commercial sectors, along with tremendous research efforts and progress. It is time to inspect the achievements of and the remaining barriers to TLS-based forest investigations, so further research and application are clearly orientated in operational uses of TLS. In such context, the international TLS benchmarking project was launched in 2014 by the European Spatial Data Research Organization and coordinated by the Finnish Geospatial Research Institute. The main objectives of this benchmarking study are to evaluate the potential of applying TLS in characterizing forests, to clarify the strengths and the weaknesses of TLS as a measure of forest digitization, and to reveal the capability of recent algorithms for tree-attribute extraction. The project is designed to benchmark the TLS algorithms by processing identical TLS datasets for a standardized set of forest attribute criteria and by evaluating the results through a common procedure respecting reliable references. Benchmarking results reflect large variances in estimating accuracies, which were unveiled through the 18 compared algorithms and through the evaluation framework, i.e., forest complexity categories, TLS data acquisition approaches, tree attributes and evaluation procedures. The evaluation framework includes three new criteria proposed in this benchmarking and the algorithm performances are investigated through combining two or more criteria (e.g., the accuracy of the individual tree attributes are inspected in conjunction with plot-level completeness) in order to reveal algorithms’ overall performance. The results also reveal some best available forest attribute estimates at this time, which clarify the status quo of TLS-based forest investigations.
@article{Liang2018, title = {International benchmarking of terrestrial laser scanning approaches for forest inventories}, journal = {ISPRS Journal of Photogrammetry and Remote Sensing}, volume = {144}, pages = {137-179}, year = {2018}, issn = {0924-2716}, doi = {https://doi.org/10.1016/j.isprsjprs.2018.06.021}, url = {https://www.sciencedirect.com/science/article/pii/S0924271618301849}, author = {Liang, Xinlian and Hyyppä, Juha and Kaartinen, Harri and Lehtomäki, Matti and Pyörälä, Jiri and Pfeifer, Norbert and Holopainen, Markus and Brolly, Gábor and Francesco, Pirotti and Hackenberg, Jan and Huang, Huabing and Jo, Hyun-Woo and Katoh, Masato and Liu, Luxia and Mokroš, Martin and Morel, Jules and Olofsson, Kenneth and Poveda-Lopez, Jose and Trochta, Jan and Wang, Di and Wang, Jinhu and Xi, Zhouxi and Yang, Bisheng and Zheng, Guang and Kankare, Ville and Luoma, Ville and Yu, Xiaowei and Chen, Liang and Vastaranta, Mikko and Saarinen, Ninni and Wang, Yunsheng}, keywords = {Benchmarking, State-of-the-art, Forest, Modeling, Point cloud, Terrestrial laser scanning, TLS}, }
Validating a workflow for tree inventory updating with 3D point clouds obtained by mobile laser scanning

Jinhu Wang and Roderik Lindenbergh

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2018

Abs Bib HTML PDF

Urban trees are an important component of our environment and ecosystem. Trees are able to combat climate change, clean the air and cool the streets and city. Tree inventory and monitoring are of great interest for biomass estimation and change monitoring. Conventionally, parameters of trees are manually measured and documented in situ, which is not efficient regarding labour and costs. Light Detection And Ranging (LiDAR) has become a well-established surveying technique for the acquisition of geo-spatial information. Combined with automatic point cloud processing techniques, this in principle enables the efficient extraction of geometric tree parameters. In recent years, studies have investigated to what extend it is possible to perform tree inventories using laser scanning point clouds. Give the availability of a city of Delft Open data tree repository, we are now able to present, validate and extend a workflow to automatically obtain tree data from tree location until tree species. The results of a test over 47 trees show that the proposed methods in the workflow are able to individual urban trees. The tree species classification results based on the extracted tree parameters show that only one tree was wrongly classified using k-means clustering.
@article{Wang2018a, author = {Wang, Jinhu and Lindenbergh, Roderik}, title = {Validating a workflow for tree inventory updating with 3D point clouds obtained by mobile laser scanning}, journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {XLII-2}, year = {2018}, pages = {1163--1168}, url = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2/1163/2018/}, doi = {10.5194/isprs-archives-XLII-2-1163-2018}, }
Scalable individual tree delineation in 3D point clouds

Jinhu Wang, Roderik Lindenbergh, and Massimo Menenti

The Photogrammetric Record 2018

Abs Bib HTML PDF

Abstract Manually monitoring and documenting trees is labour intensive. Lidar provides a possible solution for automatic tree-inventory generation. Existing approaches for segmenting trees from original point cloud data lack scalable and efficient methods that separate individual trees sampled by different laser-scanning systems with sufficient quality under all circumstances. In this study a new algorithm for efficient individual tree delineation from lidar point clouds is presented and validated. The proposed algorithm first resamples the points using cuboid (modified voxel) cells. Consecutively connected cells are accumulated by vertically traversing cell layers. Trees in close proximity are identified, based on a novel cell-adjacency analysis. The scalable performance of this algorithm is validated on airborne, mobile and terrestrial laser-scanning point clouds. Validation against ground truth demonstrates an improvement from 89% to 94% relative to a state-of-the-art method while computation time is similar.
@article{Wang2018b, author = {Wang, Jinhu and Lindenbergh, Roderik and Menenti, Massimo}, title = {Scalable individual tree delineation in 3D point clouds}, journal = {The Photogrammetric Record}, volume = {33}, number = {163}, pages = {315-340}, keywords = {cuboid, individual tree delineation, laser scanning, point cloud, 3D clustering, tree, voxel}, doi = {https://doi.org/10.1111/phor.12247}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/phor.12247}, year = {2018}, }

2017

Change analysis in structural laser scanning point clouds: The baseline method

Yueqian Shen, Roderik Lindenbergh, and Jinhu Wang

Sensors 2017

Abs Bib HTML PDF

A method is introduced for detecting changes from point clouds that avoids registration. For many applications, changes are detected between two scans of the same scene obtained at different times. Traditionally, these scans are aligned to a common coordinate system having the disadvantage that this registration step introduces additional errors. In addition, registration requires stable targets or features. To avoid these issues, we propose a change detection method based on so-called baselines. Baselines connect feature points within one scan. To analyze changes, baselines connecting corresponding points in two scans are compared. As feature points either targets or virtual points corresponding to some reconstructable feature in the scene are used. The new method is implemented on two scans sampling a masonry laboratory building before and after seismic testing, that resulted in damages in the order of several centimeters. The centres of the bricks of the laboratory building are automatically extracted to serve as virtual points. Baselines connecting virtual points and/or target points are extracted and compared with respect to a suitable structural coordinate system. Changes detected from the baseline analysis are compared to a traditional cloud to cloud change analysis demonstrating the potential of the new method for structural analysis.
@article{Shen2017, author = {Shen, Yueqian and Lindenbergh, Roderik and Wang, Jinhu}, doi = {10.3390/s17010026}, issn = {14248220}, journal = {Sensors}, keywords = {Baselines,Change detection,Masonry buildings,Structural analysis,Terrestrial laser scanning}, number = {1}, title = {{Change analysis in structural laser scanning point clouds: The baseline method}}, volume = {17}, year = {2017}, }
Scalable information extraction from point cloud data obtained by mobile laser scanner

Jinhu Wang

2017

Abs Bib HTML

The rise of intelligent transportation, autonomous driving and 3D virtual cities demands highly accurate and regularly updated 2D and 3D maps. However, traditional surveying and mapping techniques are inadequate as they are labor-intensive and cost inefficient. Mobile Laser Scanning (MLS) systems, which combine Light Detection and Ranging (LiDAR) with navigation techniques, are able to acquire highly accurate 3D measurements of road environments.
@phdthesis{WangPhDThesis2017, author = {Wang, Jinhu}, school = {Delft University of Technology}, title = {Scalable information extraction from point cloud data obtained by mobile laser scanner}, year = {2017}, }
SigVox - A 3D feature matching algorithm for automatic street object recognition in mobile laser scanning point clouds

Jinhu Wang, Roderik Lindenbergh, and Massimo Menenti

ISPRS Journal of Photogrammetry and Remote Sensing 2017

Abs Bib HTML PDF

Urban road environments contain a variety of objects including different types of lamp poles and traffic signs. Its monitoring is traditionally conducted by visual inspection, which is time consuming and expensive. Mobile laser scanning (MLS) systems sample the road environment efficiently by acquiring large and accurate point clouds. This work proposes a methodology for urban road object recognition from MLS point clouds. The proposed method uses, for the first time, shape descriptors of complete objects to match repetitive objects in large point clouds. To do so, a novel 3D multi-scale shape descriptor is introduced, that is embedded in a workflow that efficiently and automatically identifies different types of lamp poles and traffic signs. The workflow starts by tiling the raw point clouds along the scanning trajectory and by identifying non-ground points. After voxelization of the non-ground points, connected voxels are clustered to form candidate objects. For automatic recognition of lamp poles and street signs, a 3D significant eigenvector based shape descriptor using voxels (SigVox) is introduced. The 3D SigVox descriptor is constructed by first subdividing the points with an octree into several levels. Next, significant eigenvectors of the points in each voxel are determined by principal component analysis (PCA) and mapped onto the appropriate triangle of a sphere approximating icosahedron. This step is repeated for different scales. By determining the similarity of 3D SigVox descriptors between candidate point clusters and training objects, street furniture is automatically identified. The feasibility and quality of the proposed method is verified on two point clouds obtained in opposite direction of a stretch of road of 4km. 6 types of lamp pole and 4 types of road sign were selected as objects of interest. Ground truth validation showed that the overall accuracy of the 170 automatically recognized objects is approximately 95%. The results demonstrate that the proposed method is able to recognize street furniture in a practical scenario. Remaining difficult cases are touching objects, like a lamp pole close to a tree.
@article{Wang2017, author = {Wang, Jinhu and Lindenbergh, Roderik and Menenti, Massimo}, title = {SigVox - A 3D feature matching algorithm for automatic street object recognition in mobile laser scanning point clouds}, journal = {ISPRS Journal of Photogrammetry and Remote Sensing}, year = {2017}, volume = {128}, pages = {111 - 129}, doi = {https://doi.org/10.1016/j.isprsjprs.2017.03.012}, issn = {0924-2716}, keywords = {Mobile laser scanning, Point cloud, Octree, Multiple scale feature, Object recognition, 3D feature descriptor}, url = {http://www.sciencedirect.com/science/article/pii/S0924271616302003}, }

2016

A concealed car extraction method based on full-waveform LiDAR data

Chuanrong Li, Mei Zhou, Menghua Liu, Lian Ma, and Jinhu Wang

Mobile Information Systems 2016

Abs Bib

Concealed cars extraction from point clouds data acquired by airborne laser scanning has gained its popularity in recent years. However, due to the occlusion effect, the number of laser points for concealed cars under trees is not enough. Thus, the concealed cars extraction is difficult and unreliable. In this paper, 3D point cloud segmentation and classification approach based on full-waveform LiDAR was presented. This approach first employed the autocorrelation G coefficient and the echo ratio to determine concealed cars areas. Then the points in the concealed cars areas were segmented with regard to elevation distribution of concealed cars. Based on the previous steps, a strategy integrating backscattered waveform features and the view histogram descriptor was developed to train sample data of concealed cars and generate the feature pattern. Finally concealed cars were classified by pattern matching. The approach was validated by full-waveform LiDAR data and experimental results demonstrated that the presented approach can extract concealed cars with accuracy more than 78.6% in the experiment areas.
@article{Li2016, author = {Li, Chuanrong and Zhou, Mei and Liu, Menghua bit and Ma, Lian and Wang, Jinhu}, doi = {10.1155/2016/3854217}, issn = {1875905X}, journal = {Mobile Information Systems}, title = {{A concealed car extraction method based on full-waveform LiDAR data}}, year = {2016} }
High-precision 3D geolocation of persistent scatterers with one single-Epoch GCP and LIDAR DSM data

Mengshi Yang, Prabu Dheenathayalan, Ling Chang, Jinhu Wang, Roderik C. Lindenbergh, Mingsheng Liao, and Ramon F. Hanssen

In Proceedings of Living Planet Symposium 2016 2016

Abs Bib

In persistent scatterer (PS) interferometry, the relatively poor 3D geolocalization precision of the measurement points (the scatterers) is still a major concern. It makes it difficult to attribute the deformation measurements unambiguously to (elements of) physical objects. Ground control points (GCP’s), such as corner reflectors or transponders, can be used to improve geolocalization, but only in the range-azimuth domain. Here, we present a method which uses only one GCP, visible in only one single radar acquisition, in combination with a digital surface model (DSM) data to improve the geolocation precision, and to achieve an object snap by projecting the scatterer position to the intersection with the DSM model, in the metric defined by the covariance matrix (i.e. error ellipsoid) of every scatterer.
@inproceedings{Yang2016, title = {High-precision 3D geolocation of persistent scatterers with one single-Epoch GCP and LIDAR DSM data}, keywords = {Data visualisation, Image processing and data fusion, In SAR, Interferometry}, author = {Yang, Mengshi and Dheenathayalan, Prabu and Chang, Ling and Wang, Jinhu and Lindenbergh, {Roderik C.} and Liao, Mingsheng and Hanssen, {Ramon F.}}, year = {2016}, month = aug, day = {1}, language = {English}, volume = {SP-740}, series = {European Space Agency (ESA-SP)}, publisher = {European Space Agency}, pages = {398--398}, editor = {Ouwehand, L.}, booktitle = {Proceedings of Living Planet Symposium 2016}, address = {Netherlands}, note = {European Space Agency Living Planet Symposium 2016 ; Conference date: 09-05-2016 Through 13-05-2016}, url = {http://lps16.esa.int/} }
Coarse point cloud registration by EGI matching of voxel clusters

Jinhu Wang, Roderik Lindenbergh, Yueqian Shen, and Massimo Menenti

ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences 2016

Abs Bib HTML PDF

Laser scanning samples the surface geometry of objects efficiently and records versatile information as point clouds. However, often more scans are required to fully cover a scene. Therefore, a registration step is required that transforms the different scans into a common coordinate system. The registration of point clouds is usually conducted in two steps, ie coarse registration followed by fine registration. In this study an automatic marker-free coarse registration method for pair-wise scans is presented. First the two input point clouds are re-sampled as voxels and dimensionality features of the voxels are determined by principal component analysis (PCA). Then voxel cells with the same dimensionality are clustered. Next, the Extended Gaussian Image (EGI) descriptor of those voxel clusters are constructed using significant eigenvectors of each voxel in the cluster. Correspondences between clusters in source and target data are obtained according to the similarity between their EGI descriptors. The random sampling consensus (RANSAC) algorithm is employed to remove outlying correspondences until a coarse alignment is obtained. If necessary, a fine registration is performed in a final step. This new method is illustrated on scan data sampling two indoor scenarios. The results of the tests are evaluated by computing the point to point distance between the two input point clouds. The presented two tests resulted in mean distances of 7.6 mm and 9.5 mm respectively, which are adequate for fine registration.
@article{Wang2016, author = {Wang, Jinhu and Lindenbergh, Roderik and Shen, Yueqian and Menenti, Massimo}, title = {Coarse point cloud registration by EGI matching of voxel clusters}, journal = {ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {III-5}, year = {2016}, pages = {97--103}, url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-5/97/2016/}, doi = {10.5194/isprs-annals-III-5-97-2016}, }

2015

Automated large scale parameter extraction of road-side trees sampled by a laser mobile mapping system

Roderik Lindenbergh, Ditmar Berthold, Beril Sirmacek, Monica Herrero-Huerta, Jinhu Wang, and D. Ebersbach

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2015

Abs Bib HTML PDF

In urbanized Western Europe trees are considered an important component of the built-up environment. This also means that there is an increasing demand for tree inventories. Laser mobile mapping systems provide an efficient and accurate way to sample the 3D road surrounding including notable roadside trees. Indeed, at, say, 50 km/h such systems collect point clouds consisting of half a million points per 100m. Method exists that extract tree parameters from relatively small patches of such data, but a remaining challenge is to operationally extract roadside tree parameters at regional level. For this purpose a workflow is presented as follows: The input point clouds are consecutively downsampled, retiled, classified, segmented into individual trees and upsampled to enable automated extraction of tree location, tree height, canopy diameter and trunk diameter at breast height (DBH). The workflow is implemented to work on a laser mobile mapping data set sampling 100 km of road in Sachsen, Germany and is tested on a stretch of road of 7km long. Along this road, the method detected 315 trees that were considered well detected and 56 clusters of tree points were no individual trees could be identified. Using voxels, the data volume could be reduced by about 97% in a default scenario. Processing the results of this scenario took 2500 seconds, corresponding to about 10 km/h, which is getting close to but is still below the acquisition rate which is estimated at 50 km/h.
@article{Lindenbergh2015, author = {Lindenbergh, Roderik and Berthold, Ditmar and Sirmacek, Beril and Herrero-Huerta, Monica and Wang, Jinhu and Ebersbach, D.}, title = {Automated large scale parameter extraction of road-side trees sampled by a laser mobile mapping system}, journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {XL-3/W3}, year = {2015}, pages = {589--594}, url = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-3-W3/589/2015/}, doi = {10.5194/isprsarchives-XL-3-W3-589-2015}, }
Evaluating voxel enabled scalable intersection of large point clouds

Jinhu Wang, Roderik Lindenbergh, and Massimo Menenti

ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences 2015

Abs Bib HTML PDF

Laser scanning has become a well established surveying solution for obtaining 3D geo-spatial information on objects and environment. Nowadays scanners acquire up to millions of points per second which makes point cloud huge. Laser scanning is widely applied from airborne, carborne and stable platforms, resulting in point clouds obtained at different attitudes and with different extents. Working with such different large point clouds makes the determination of their overlapping area necessary but often time consuming. In this paper, a scalable point cloud intersection determination method is presented based on voxels. The method takes two overlapping point clouds as input. It consecutively resamples the input point clouds according to a preset voxel cell size. For all non-empty cells the center of gravity of the points in contains is computed. Consecutively for those centers it is checked if they are in a voxel cell of the other point cloud. The same process is repeated after interchanging the role of the two point clouds. The quality of the results is evaluated by the distance to the pints from the other data set. Also computation time and quality of the results are compared for different voxel cell sizes. The results are demonstrated on determining he intersection between an airborne and carborne laser point clouds and show that the proposed method takes 0.10%, 0.15%, 1.26% and 14.35% of computation time compared the the classic method when using cell sizes of of 10, 8, 5 and 3 meters respectively.
@article{Wang2015, author = {Wang, Jinhu and Lindenbergh, Roderik and Menenti, Massimo}, title = {Evaluating voxel enabled scalable intersection of large point clouds}, journal = {ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {II-3/W5}, year = {2015}, pages = {25--31}, url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W5/25/2015/}, doi = {10.5194/isprsannals-II-3-W5-25-2015}, }
IQPC 2015 Track: Tree separation and classification in mobile mapping LiDAR data

Ben Gorte, Sander Oude Elberink, Beril Sirmacek, and Jinhu Wang

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2015

Abs Bib HTML PDF

The European FP7 project IQmulus yearly organizes several processing contests, where submissions are requested for novel algorithms for point cloud and other big geodata processing. This paper describes the set-up and execution of a contest having the purpose to evaluate state-of-the-art algorithms for Mobile Mapping System point clouds, in order to detect and identify (individual) trees. By the nature of MMS these are trees in the vicinity of the road network (rather than in forests). Therefore, part of the challenge is distinguishing between trees and other objects, such as buildings, street furniture, cars etc. Three submitted segmentation and classification algorithms are thus evaluated.
@article{Ben2015, author = {Gorte, Ben and Oude Elberink, Sander and Sirmacek, Beril and Wang, Jinhu}, title = {IQPC 2015 Track: Tree separation and classification in mobile mapping LiDAR data}, journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {XL-3/W3}, year = {2015}, pages = {607--612}, url = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-3-W3/607/2015/}, doi = {10.5194/isprsarchives-XL-3-W3-607-2015}, }

2014

Geometric road runoff estimation from laser mobile mapping data

Jinhu Wang, Higinio González-Jorge, Roderik Lindenbergh, Pedro Arias-Sánchez, and Massimo Menenti

ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences 2014

Abs Bib HTML PDF

Mountain roads are the lifelines of remote areas but are often situated in complicated settings and prone to landslides, rock fall, avalanches and damages due to surface water runoff. The impact and likelihood of these types of hazards can be partly assessed by a detailed geometric analysis of the road environment. Field measurements in remote areas are expensive however. A possible solution is the use of a Laser Mobile Mapping System (LMMS) which, at high measuring rate, captures dense and accurate point clouds. This paper presents an automatic approach for the delineation of both the direct environment of a road and the road itself into local catchments starting from a LMMS point cloud. The results enable a user to assess where on the road most water from the surroundings will assemble, and how water will flow over the road after eg heavy snow melt or rainfall. To arrive at these results the following steps are performed. First outliers are removed and point cloud data is gridded at a uniform width. Local surface normal and gradient of each grid point are determined. The relative smoothness of the road is used as a criterion to identify the road’s outlines. The local gradients are input for running the so-called D8 method, which simply exploits that surface water follows the direction of steepest descent. This method first enables the identification of sinks on the roadside, ie the locations where water flow accumulates and potentially enters the road. Moreover, the method divides the road’s direct neighbourhood into catchments, each consisting of all grid cells having runoff to the same sink. In addition the method is used to analyse the surface. The new method is demonstrated on a piece of 153 meters long Galician mountain road as sampled by LMMS data.
@article{Wang2014, author = {Wang, Jinhu and Gonz\'{a}lez-Jorge, Higinio and Lindenbergh, Roderik and Arias-S\'{a}nchez, Pedro and Menenti, Massimo}, title = {Geometric road runoff estimation from laser mobile mapping data}, journal = {ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {II-5}, year = {2014}, pages = {385--391}, url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-5/385/2014/}, doi = {10.5194/isprsannals-II-5-385-2014}, }

2013

Automatic estimation of excavation volume from laser mobile mapping data for mountain road widening

Jinhu Wang, Higinio González-Jorge, Roderik Lindenbergh, Pedro Arias-Sánchez, and Massimo Menenti

Remote Sensing 2013

Abs Bib HTML PDF

Roads play an indispensable role as part of the infrastructure of society. In recent years, society has witnessed the rapid development of laser mobile mapping systems (LMMS) which, at high measurement rates, acquire dense and accurate point cloud data. This paper presents a way to automatically estimate the required excavation volume when widening a road from point cloud data acquired by an LMMS. Firstly, the input point cloud is down-sampled to a uniform grid and outliers are removed. For each of the resulting grid points, both on and off the road, the local surface normal and 2D slope are estimated. Normals and slopes are consecutively used to separate road from off-road points which enables the estimation of the road centerline and road boundaries. In the final step, the left and right side of the road points are sliced in 1-m slices up to a distance of 4 m, perpendicular to the roadside. Determining and summing each sliced volume enables the estimation of the required excavation for a widening of the road on the left or on the right side. The procedure, including a quality analysis, is demonstrated on a stretch of a mountain road that is approximately 132 m long as sampled by a Lynx LMMS. The results in this particular case show that the required excavation volume on the left side is 8% more than that on the right side. In addition, the error in the results is assessed in two ways. First, by adding up estimated local errors, and second, by comparing results from two different datasets sampling the same piece of road both acquired by the Lynx LMMS. Results of both approaches indicate that the error in the estimated volume is below 4%. The proposed method is relatively easy to implement and runs smoothly on a desktop PC. The whole workflow of the LMMS data acquisition and subsequent volume computation can be completed in one or two days and provides road engineers with much more detail than traditional single-point surveying methods such as Total Station or GPS profiling. A drawback is that an LMMS system can only sample what is within the view of the system from the road.
@article{Wang2013, author = {Wang, Jinhu and Gonz\'{a}lez-Jorge, Higinio and Lindenbergh, Roderik and Arias-S\'{a}nchez, Pedro and Menenti, Massimo}, title = {Automatic estimation of excavation volume from laser mobile mapping data for mountain road widening}, journal = {Remote Sensing}, year = {2013}, volume = {5}, pages = {4629--4651}, number = {9}, doi = {10.3390/rs5094629}, issn = {2072-4292}, url = {http://www.mdpi.com/2072-4292/5/9/4629}, }

2012

A comparison of two differnt approaches of point cloud classification based on full-waveform LiDAR data

Jinhu Wang, Chuanrong Li, Lingli Tang, Mei Zhou, and Jingmei Li

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2012

Abs Bib HTML PDF

In this paper, two different point cloud classification approaches were applied based on the full-waveform LiDAR data. At the beginning, based on the full-waveform LiDAR data, we decomposed the backscattered pulse waveform and abstracted each component in the waveform after the pre-processing of noise detection and waveform smoothing. And by the time flag of each component acquired in the decomposition procedure we calculated the three dimension coordination of the component. Then the components’ waveform properties, including amplitude, width and cross-section, were uniformed respectively and formed the Amplitude/Width/Section space. Then two different approaches were applied to classify the points. First, we selected certain targets and trained the parameters, after that, by the supervised classification way we segmented the study area point. On the other hand, we apply the IHSL colour transform to the above space to find a new space, RGB colour space, which has a uniform distinguishability among the parameters and contains the whole information of each component in Amplitude/Width/Section space. Then the fuzzy C-means algorithm is applied to the derived RGB space to complete the LiDAR point classification procedure. By comparing the two different segmentation results, which may of substantial importance for further targets detection and identification, a brief discussion and conclusion were brought out for further research and study.
@article{Wang2012, author = {Wang, Jinhu and Li, Chuanrong and Tang, Lingli and Zhou, Mei and Li, Jingmei}, title = {A comparison of two differnt approaches of point cloud classification based on full-waveform LiDAR data}, journal = {ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, volume = {XXXIX-B3}, year = {2012}, pages = {179--182}, url = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B3/179/2012/}, doi = {10.5194/isprsarchives-XXXIX-B3-179-2012}, }