Hangbin Wu
Papers
3
Total Citations
12
H-Index
3
About
Hangbin Wu is a leading researcher in visual odometry, indoor mapping, and point cloud processing, whose work directly addresses the challenges of autonomous navigation in complex environments. His most impactful contribution is a multi-layer fusion image enhancement method for visual odometry under poor visibility scenarios—cited 6 times—which tackles the critical problem of degraded robot performance in weak illumination, low-texture, and self-similar conditions. This innovation is vital for robotic rescue and navigation operations where reliable vision is essential. Wu also advances indoor high-precision mapping through a normalized total least squares approach for map boundary correction (3 citations), solving the practical issue of raw, irregular indoor maps that hinder robot navigation and location-based services. Additionally, his intelligent classification of point clouds for indoor components via dimensionality reduction (3 citations) addresses the difficulty of processing sparse, disordered LiDAR and RGBD data. By fusing sensor data with robust mathematical methods, Wu’s work directly improves the reliability of autonomous systems in real-world, challenging scenarios.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3