A5022640746- 3D Shape Modeling and Analysis
- Remote Sensing and LiDAR Applications
- Inertial Sensor and Navigation
- 3D Surveying and Cultural Heritage
- Advanced Numerical Analysis Techniques
- Robotics and Sensor-Based Localization
- Indoor and Outdoor Localization Technologies
- Forest ecology and management
- Forest Management and Policy
- Image and Signal Denoising Methods
- Surface Roughness and Optical Measurements
- Advanced Image Processing Techniques
- Image Processing and 3D Reconstruction
- Advanced Vision and Imaging
- Computer Graphics and Visualization Techniques
- Advanced Optical Sensing Technologies
Nanjing University
2021-2025
University of Chinese Academy of Sciences
2024
Fitting primitives for point cloud data to obtain a structural representation has been widely adopted reverse engineering and other graphics applications. Existing segmentation-based approaches only segment primitive patches but ignore edges that indicate boundaries of primitives, leading inaccurate incomplete reconstruction. To fill the gap, we present novel surface edge detection network (SED-Net) accurate geometric fitting clouds. The key idea is learn parametric surfaces (including...
Parametric edge reconstruction for point cloud data is a fundamental problem in computer graphics. Existing methods first classify points as either (including corners) or non-edge points, and then fit parametric edges to the points. However, few are exactly sampled on practical scenarios, leading significant fitting errors reconstructed edges. Prominent deep learning-based also primarily emphasize overlooking potential of areas. Given that sparse non-uniform cannot provide adequate...
Aboveground biomass (AGB) of shrubs and low-statured trees constitutes a substantial portion the total carbon pool in temperate forest ecosystems, contributing much to local biodiversity, altering tree-regeneration growth rates, determining above- belowground food webs. Accurate quantification AGB at shrub layer is crucial for ecological modeling still remains challenge. Several methods estimating understory biomass, including inventory remote sensing-based methods, need be evaluated against...
Abstract Due to the fragility of single-sensor positioning technology in complex scenarios, especially urban areas, multi-sensor is becoming increasingly popular. To further improve robustness system by fully utilizing information from various sensors, this article proposes a differential-GNSS-visual-inertial navigation (DGVINS) that tightly fuses differential global satellite (GNSS), vision and inertial provide accurate, robust seamless position for intelligent applications. DGVINS...
Abstract Due to the fragility of single-sensor positioning technology in complex scenarios, especially urban areas, multi-sensor is becoming increasingly popular. To further improve robustness system by fully utilizing information from various sensors, this article proposes a differential-GNSS-visual-inertial navigation (DGVINS) that tightly fuses differential global satellite (GNSS), vision and inertial provide accurate, robust seamless position for intelligent applications. DGVINS...
We propose a new video vectorization approach for converting videos in the raster format to vector representation with benefits of resolution independence and compact storage. Through classifying extracted curves each frame into salient ones non-salient ones, we introduce novel bipartite diffusion (BDCs) order preserve both important image features such as sharp boundaries regions smooth color variation. This allows us propagate across frames that propagation, conjunction geometry...