POST: Visual Navigation by Integrating Panoramic Vision, Omnidirectional Vision and Stereo Vision
Project Status: Complete (Years: 1991 – 2000)
Visual navigation of a mobile robot in a natural environment has always been a very interesting but challenging problem. It involves almost every aspect of computer vision research – from visual sensors through robust algorithms to visual representations. The basic requirements of visual navigation include global localization (to decide where to go), road following (to stay on the road) and obstacle detection (to avoid collision). Only after these safety requirements have been satisfied, which have been proven to be not a trivial problem, can the robot pursue other task-oriented goals. It is clear that visual environment modeling is the foundation of these basic issues in visual navigation – and it may extend to most of the real world problems in computer vision.
China National Advanced Research Program, Image Mosaic-based Visual Scene Modeling and Target Recognition, 1/1996-12/2000, Co-PIs: G. Xu, Z. Zhu
China National Science Foundation, Image Stabilization Technique for Mobile Robot, 06/1995- 09/1997, PI: Z. Zhu
China National Science Foundation, Motion Estimation Using Gradients of Image Intensity, 1/1994-12/1996, Co-PI: Z. Zhu
China National Advanced Research Program, Comprehensive Understanding of Multiple Sensing Systems, 1/1991-12/1995, Co-PIs: G. Xu, Z. Zhu