Research Interests
3D laser scanning technology has demonstrated great potential in the field of environmental remote sensing due to its ability to efficiently acquire high-density and accurate spatial information. Its automated and precise capture of surface conditions and structural geometry makes it an ideal tool for large-scale terrain modeling, vegetation structure analysis, and ecological monitoring. With the increasing availability of airborne and UAV-based LiDAR systems, massive point cloud datasets are being generated, offering new opportunities for understanding complex environmental systems.
My research primarily focuses on point cloud processing and understanding, including 3D object detection, segmentation, and reconstruction. These core techniques serve as the foundation for a wide range of remote sensing applications such as forest inventory analysis, vegetation coverage estimation, terrain surface modeling, and natural resource monitoring. By leveraging advanced deep learning methods, I aim to enhance the semantic interpretation and geometric understanding of LiDAR point clouds in diverse environmental contexts.
Education
- PhD in Systems Design Engineering, University of Waterloo, Canada, 2025
- MSc, College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, China, 2021
- BSc, College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, China, 2018
Publications
- Lu, Dening, et al. 3D-UMamba: 3D U-Net with state space model for semantic segmentation of multi-source LiDAR point clouds. International Journal of Applied Earth Observation and Geoinformation 136 (2025): 104401.
- Lu, Dening, et al. Integrating deep transformer and temporal convolutional networks for SMEs revenue and employment growth prediction. Expert Systems with Applications 252 (2024): 124129.
- Lu, Dening, et al. 3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classication and Segmentation. IEEE Transactions on Geoscience and Remote Sensing 62 (2024): 1-13.
- Lu, Dening, et al. 3DCTN: 3D Convolution-Transformer Network for Point Cloud Classication. IEEE Transactions on Intelligent Transportation Systems 23.12 (2022): 24854-24865.
- Lu, Dening, et al. Dynamic clustering transformer network for point cloud segmentation. International Journal of Applied Earth Observation and Geoinformation 128 (2024): 103791.
- Gao, Kyle, Lu, Dening, et al. Enhanced 3D Urban Scene Reconstruction and Point Cloud Densication using Gaussian Splatting and Google Earth Imagery. IEEE Transactions on Geoscience and Remote Sensing (2025).
- Wang, Lanying, Lu, Dening, et al. Individual tree species classication using low-density airborne multispectral LiDAR data via attribute-aware cross-branch transformer. Remote Sensing of Environment 315 (2024): 114456.