Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Activity monitoring, a crucial task in many applications, is often conducted expensively using video cameras. Also, effectively monitoring a large field by analyzing images from m...
Yunhao Liu, Lei Chen 0002, Jian Pei, Qiuxia Chen, ...
— Tracking of miniature robotic platforms involves major challenges in image recognition and data association. We present our 3-year effort into developing the platform-independe...
Polygonal meshes obtained from acquisition of real-world objects may easily exhibit topological or geometrical defects, which often prevent subsequent processing and analysis to p...