Chang Liang
Papers
1
Total Citations
3
H-Index
1
About
Chang Liang is a pioneering researcher in the intersection of computer vision, deep learning, and robotic navigation. His primary research areas include visual simultaneous localization and mapping (SLAM), panoramic perception systems, and semantic scene understanding for autonomous robots. Liang’s most notable contribution is the development of Deep ViDAR, a CNN-based 360° panoramic video system that reimagines outdoor robot navigation by replacing traditional laser radar with deep learning-driven visual semantic segmentation. This innovative approach leverages the fixed semantic cues in outdoor environments—such as road structures—to enable robust, cost-effective navigation and SLAM without expensive LiDAR hardware. Although his seminal 2018 paper on Deep ViDAR has garnered 3 citations to date, its conceptual impact lies in bridging semantic image segmentation with real-time robotic perception, offering a scalable alternative for autonomous systems. Liang’s work demonstrates a forward-thinking integration of panoramic imagery and convolutional neural networks, positioning him as a key contributor to the evolution of vision-based robotics. His research continues to inspire new directions in affordable, intelligent navigation for outdoor autonomous vehicles.
Research Focus
Key Achievements
Top Papers
- 1