Yueqian Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yueqian Shen has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Dong Chen
College of Civil Engineering, Nanjing Forestry University, Nanjing 210037, China
9 shared publications - Vagner Gonçalves Ferreira
School of Earth Sciences and Engineering, Hohai University, Nanjing, China
9 shared publications - Yanming Chen
School of Earth Sciences and Engineering, Hohai University, Nanjing, China
9 shared publications Jinguo Wang
7 shared publications- Jinguo Wang
School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China
7 shared publications Jinhu Wang
5 shared publications
Latest Publications
- Open Access
- 16 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (20) , 3558
Fallen Tree Detection and Mapping from Airborne Laser Scanning Point Clouds Using Physics-Guided Supervoxel Learning
Accurate fallen tree detection from airborne laser scanning (ALS) point clouds is important for forest structural assessment and disturbance monitoring. However, fallen trees remain difficult to extract from operational ALS data because near-ground stems are often fragmented by understory occlusion, uneven sampling, and geometric confusion with shrubs, terrain surfaces, and other low vegetation. This study proposes a physics-guided supervoxel framework for fallen tree detection from ALS point clouds. The framework represents ALS observations as spatially coherent supervoxels and describes each supervoxel using local geometric features, cylindrical morphology, and graph-based neighborhood context. Cylindrical descriptors encode the elongated stem structure of fallen trees, while graph-topological features represent spatial continuity among adjacent supervoxels. A stacking ensemble classifier is trained with SHAP-based feature selection, followed by graph-constrained spatial refinement to improve local label consistency. The framework was trained using 30 plots and evaluated on seven held-out forest plots from the Dutch Actueel Hoogtebestand Nederland 4 (AHN4) dataset, with point densities of 10–15 pts/m2. Using point-level reference labels, the stacking classifier achieved a mean fallen tree F1-score of 83.86% across the test plots, which increased to 85.39% after spatial refinement. Ablation results show that cylindrical descriptors provided the largest gain, improving the fallen tree F1 score by 11.77%. These results indicate that physics-guided supervoxel learning can produce interpretable fallen tree maps from operational ALS data and support subsequent analyses of near-ground forest structure and disturbance effects.
- 16 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (20) , 3558
Open AccessFallen Tree Detection and Mapping from Airborne Laser Scanning Point Clouds Using Physics-Guided Supervoxel Learning
Accurate fallen tree detection from airborne laser scanning (ALS) point clouds is important for forest structural assessment and disturbance monitoring. However, fallen trees remain difficult to extract from operational ALS data because near-ground stems are often fragmented by understory occlusion, uneven sampling, and geometric confusion with shrubs, terrain surfaces, and other low vegetation. This study proposes a physics-guided supervoxel framework for fallen tree detection from ALS point clouds. The framework represents ALS observations as spatially coherent supervoxels and describes each supervoxel using local geometric features, cylindrical morphology, and graph-based neighborhood context. Cylindrical descriptors encode the elongated stem structure of fallen trees, while graph-topological features represent spatial continuity among adjacent supervoxels. A stacking ensemble classifier is trained with SHAP-based feature selection, followed by graph-constrained spatial refinement to improve local label consistency. The framework was trained using 30 plots and evaluated on seven held-out forest plots from the Dutch Actueel Hoogtebestand Nederland 4 (AHN4) dataset, with point densities of 10–15 pts/m2. Using point-level reference labels, the stacking classifier achieved a mean fallen tree F1-score of 83.86% across the test plots, which increased to 85.39% after spatial refinement. Ablation results show that cylindrical descriptors provided the largest gain, improving the fallen tree F1 score by 11.77%. These results indicate that physics-guided supervoxel learning can produce interpretable fallen tree maps from operational ALS data and support subsequent analyses of near-ground forest structure and disturbance effects.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4625-4632
CT-FLO: Simple Yet Effective FMCW LiDAR Odometry Using an Linear Continuous-Time Trajectory
Frequency-Modulated Continuous-Wave (FMCW) LiDAR is capable of acquiring dense point clouds along with additional Doppler measurements. For discrete-time-based FMCW LiDAR odometry methods, motion distortion correction for both 3D and Doppler measurements should be performed before scan matching. However, this correction is inherently less accurate than continuous-time methods, and the residual errors are challenging to model. In this paper, we introduce CT-FLO, the first FMCW LiDAR odometry method that employs a linear continuous-time trajectory representation. Our method employs a sliding-window-based factor graph that incorporates point-to-plane factors, Doppler velocity factors, and a marginalization factor. We evaluate the proposed method on real-world datasets and demonstrate that it achieves excellent performance compared to state-of-the-art methods. The average root mean square of translational RPE, calculated using 100-meter sub-trajectories, was 1.7 m on geometrically challenging sequences and 0.19 m on feature-rich urban sequences. Additionally, an ablation study was conducted to investigate the contribution of the Doppler factor. We found that in a feature-rich environment with a longer time interval (e.g., 100 ms) for the control points, the Doppler factor can have a negative impact on the overall accuracy. Furthermore, we performed comparative experiments that determined the optimal time interval on a vehicle platform to be 40 ms for the test dataset. These results indicate that the optimal time interval is closely correlated with the geometric structure of the environment and the vehicle’s motion state.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4625-4632
CT-FLO: Simple Yet Effective FMCW LiDAR Odometry Using an Linear Continuous-Time Trajectory
Frequency-Modulated Continuous-Wave (FMCW) LiDAR is capable of acquiring dense point clouds along with additional Doppler measurements. For discrete-time-based FMCW LiDAR odometry methods, motion distortion correction for both 3D and Doppler measurements should be performed before scan matching. However, this correction is inherently less accurate than continuous-time methods, and the residual errors are challenging to model. In this paper, we introduce CT-FLO, the first FMCW LiDAR odometry method that employs a linear continuous-time trajectory representation. Our method employs a sliding-window-based factor graph that incorporates point-to-plane factors, Doppler velocity factors, and a marginalization factor. We evaluate the proposed method on real-world datasets and demonstrate that it achieves excellent performance compared to state-of-the-art methods. The average root mean square of translational RPE, calculated using 100-meter sub-trajectories, was 1.7 m on geometrically challenging sequences and 0.19 m on feature-rich urban sequences. Additionally, an ablation study was conducted to investigate the contribution of the Doppler factor. We found that in a feature-rich environment with a longer time interval (e.g., 100 ms) for the control points, the Doppler factor can have a negative impact on the overall accuracy. Furthermore, we performed comparative experiments that determined the optimal time interval on a vehicle platform to be 40 ms for the test dataset. These results indicate that the optimal time interval is closely correlated with the geometric structure of the environment and the vehicle’s motion state.
- Open Access
- 21 January 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (2) , 362
High-Precision River Network Mapping Using River Probability Learning and Adaptive Stream Burning
Accurate river network mapping is essential for hydrological modeling, flood risk assessment, and watershed environment management. However, conventional methods based on either optical imagery or digital elevation models (DEMs) often suffer from river network discontinuity and poor representation of morphologically complex rivers. To overcome this limitation, this study proposes a novel method integrating the river-oriented Gradient Boosting Tree model (RGBT) and adaptive stream burning algorithm for high-precision and topologically consistent river network extraction. Water-oriented multispectral indices and multi-scale linear geometric features are first fused and input for a river-oriented Gradient Boosting Tree model to generate river probability maps. A direction-constrained region growing strategy is then applied to derive spatially coherent river vectors. These vectors are finally integrated into a spatially adaptive stream burning algorithm to construct a conditional DEM for hydrological coherent river network extraction. We select eight representative regions with diverse topographical characteristics to evaluate the performance of our method. Quantitative comparisons against reference networks and mainstream hydrographic products demonstrate that the method achieves the highest positional accuracy and network continuity, with errors mainly focused within a 0–40 m range. Significant improvements are primarily for narrow tributaries, highly meandering rivers, and braided channels. The experiments demonstrate that the proposed method provides a reliable solution for high-resolution river network mapping in complex environments.
- 21 January 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (2) , 362
Open AccessHigh-Precision River Network Mapping Using River Probability Learning and Adaptive Stream Burning
Accurate river network mapping is essential for hydrological modeling, flood risk assessment, and watershed environment management. However, conventional methods based on either optical imagery or digital elevation models (DEMs) often suffer from river network discontinuity and poor representation of morphologically complex rivers. To overcome this limitation, this study proposes a novel method integrating the river-oriented Gradient Boosting Tree model (RGBT) and adaptive stream burning algorithm for high-precision and topologically consistent river network extraction. Water-oriented multispectral indices and multi-scale linear geometric features are first fused and input for a river-oriented Gradient Boosting Tree model to generate river probability maps. A direction-constrained region growing strategy is then applied to derive spatially coherent river vectors. These vectors are finally integrated into a spatially adaptive stream burning algorithm to construct a conditional DEM for hydrological coherent river network extraction. We select eight representative regions with diverse topographical characteristics to evaluate the performance of our method. Quantitative comparisons against reference networks and mainstream hydrographic products demonstrate that the method achieves the highest positional accuracy and network continuity, with errors mainly focused within a 0–40 m range. Significant improvements are primarily for narrow tributaries, highly meandering rivers, and braided channels. The experiments demonstrate that the proposed method provides a reliable solution for high-resolution river network mapping in complex environments.
- 18 December 2025
- Published by Elsevier in Measurement
- Vol. 263
Intensity-aware leakage segmentation in subway shield tunnels: a global-local descriptor framework with CatBoost for MLS point clouds
- 18 December 2025
- Published by Elsevier in Measurement
- Vol. 263
Intensity-aware leakage segmentation in subway shield tunnels: a global-local descriptor framework with CatBoost for MLS point clouds
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 14 (1) , 335-361
Public Building Geometric Models From Point Clouds: A multidimensional quality evaluation framework
With the rapid development of the low-altitude economy, the application of 3D building geometric models has become increasingly critical in fields such as urban planning and management, disaster emergency response, virtual reality, augmented reality, and digital twins. Due to the advancements in fundamental surveying and mapping technologies as well as computer vision, datasets of building geometric models based on ubiquitous point clouds have continuously emerged. However, the created models often suffer from low lightweight properties, strong dependence on prior knowledge of building structures, topological inconsistency, and insufficient or even absent semantic representation. These problems have resulted in building model datasets exhibiting significant disparities in geometric accuracy, topological structure, and semantic richness, alongside a lack of unified quality assessment standards. To address this, this article proposes a multidimensional quality evaluation framework for building geometric models, encompassing aspects such as geometric accuracy, topological correctness, semantic richness, lightweight properties, and model modality. This framework is employed to comprehensively evaluate six representative building model datasets. By examining common issues in existing datasets, such as geometric distortions, topological errors, and semantic deficiencies, a series of optimization strategies and solutions are proposed. Considering diverse application requirements, this article emphasizes balance among geometric accuracy, topological relationships, semantic richness, and lightweight to meet the demands of multiscenario applications. Furthermore, the article explores future directions for the construction of building model datasets, recommending a focus on multilevel detail representation, uncertainty assessment of quality, and alignment with practical application demands. These efforts aim to drive the optimization and intelligent development of 3D building models, providing higherquality support for applications such as digital twins and the low-altitude economy.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 14 (1) , 335-361
Public Building Geometric Models From Point Clouds: A multidimensional quality evaluation framework
With the rapid development of the low-altitude economy, the application of 3D building geometric models has become increasingly critical in fields such as urban planning and management, disaster emergency response, virtual reality, augmented reality, and digital twins. Due to the advancements in fundamental surveying and mapping technologies as well as computer vision, datasets of building geometric models based on ubiquitous point clouds have continuously emerged. However, the created models often suffer from low lightweight properties, strong dependence on prior knowledge of building structures, topological inconsistency, and insufficient or even absent semantic representation. These problems have resulted in building model datasets exhibiting significant disparities in geometric accuracy, topological structure, and semantic richness, alongside a lack of unified quality assessment standards. To address this, this article proposes a multidimensional quality evaluation framework for building geometric models, encompassing aspects such as geometric accuracy, topological correctness, semantic richness, lightweight properties, and model modality. This framework is employed to comprehensively evaluate six representative building model datasets. By examining common issues in existing datasets, such as geometric distortions, topological errors, and semantic deficiencies, a series of optimization strategies and solutions are proposed. Considering diverse application requirements, this article emphasizes balance among geometric accuracy, topological relationships, semantic richness, and lightweight to meet the demands of multiscenario applications. Furthermore, the article explores future directions for the construction of building model datasets, recommending a focus on multilevel detail representation, uncertainty assessment of quality, and alignment with practical application demands. These efforts aim to drive the optimization and intelligent development of 3D building models, providing higherquality support for applications such as digital twins and the low-altitude economy.
- 13 September 2025
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 230, 18-31
Contextual boundary-aware network for semantic segmentation of complex land transportation point cloud scenes
- 13 September 2025
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 230, 18-31
Contextual boundary-aware network for semantic segmentation of complex land transportation point cloud scenes
- 22 August 2025
- Published by Elsevier in Measurement
- Vol. 257
Advances and challenges in water leakage detection techniques for shield tunnels: a comprehensive review
- 22 August 2025
- Published by Elsevier in Measurement
- Vol. 257
Advances and challenges in water leakage detection techniques for shield tunnels: a comprehensive review
- 24 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
PGFormer: A Point Cloud Segmentation Network for Urban Scenes Combining Grouped Transformer and KPConv
Semantic segmentation of large-scale point cloud urban scenes faces significant challenges due to the complexity and diversity of object distribution. Transformer can effectively model the long-range dependencies in large-scale urban scenes, facilitating a comprehensive understanding of the overall structure and global context of urban scenes. Owing to the inherent strengths of the Transformer architecture, an increasing number of studies have applied it to the processing of large-scale point cloud data in complex scenes. But the excessive focus on global relationship inevitably leads to information redundancy, which can affect the model’s performance. To address this issue, we propose a novel Point Cloud Urban Scenes Semantic Segmentation network called PGFormer. This network consists of our proposed Group Representation Transformer (GRT) and KPConv, ensuring the enhancement of local key information while preserving global context. Specifically, in the proposed GRT block, we compute group-based and feature-based attention maps for Q and K across different groupings, and obtain the final attention output by integrating these with the global V, which has been pre-embedded with positional encoding derived from a triangular function. Our model is tested on two MLS (Paris-Lille-3D, Toronto3D) datasets and two ALS (Hessigheim 3D, ISPRS Vaihingen) datasets, and compared with a range of state-of-the-art (SOTA) methods, demonstrating the outstanding performance of our approach. Among various land cover segmentation tasks, our model achieves best or second-best results, particularly attaining the best OA (99.1%) and mF1-score (90.9%) on the Lille2 subset. Codes are available at https://github.com/Kange7/PGFormer.
- 24 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
PGFormer: A Point Cloud Segmentation Network for Urban Scenes Combining Grouped Transformer and KPConv
Semantic segmentation of large-scale point cloud urban scenes faces significant challenges due to the complexity and diversity of object distribution. Transformer can effectively model the long-range dependencies in large-scale urban scenes, facilitating a comprehensive understanding of the overall structure and global context of urban scenes. Owing to the inherent strengths of the Transformer architecture, an increasing number of studies have applied it to the processing of large-scale point cloud data in complex scenes. But the excessive focus on global relationship inevitably leads to information redundancy, which can affect the model’s performance. To address this issue, we propose a novel Point Cloud Urban Scenes Semantic Segmentation network called PGFormer. This network consists of our proposed Group Representation Transformer (GRT) and KPConv, ensuring the enhancement of local key information while preserving global context. Specifically, in the proposed GRT block, we compute group-based and feature-based attention maps for Q and K across different groupings, and obtain the final attention output by integrating these with the global V, which has been pre-embedded with positional encoding derived from a triangular function. Our model is tested on two MLS (Paris-Lille-3D, Toronto3D) datasets and two ALS (Hessigheim 3D, ISPRS Vaihingen) datasets, and compared with a range of state-of-the-art (SOTA) methods, demonstrating the outstanding performance of our approach. Among various land cover segmentation tasks, our model achieves best or second-best results, particularly attaining the best OA (99.1%) and mF1-score (90.9%) on the Lille2 subset. Codes are available at https://github.com/Kange7/PGFormer.