A multi-hypothesis approach for salient object tracking in visual surveillance

In this paper we describe a control methodology for catching a fast moving object with a robot manipulator, where visual information is employed to track the trajectory of the target. Sensing, planning and control are performed in real-time t

通过基于一组目标模板找到具有最小重建误差的最佳候选区域，将稀疏表示应用于视觉跟踪。(Sparse representations have been applied to visual tracking by finding the best candidate region with minimal reconstruction error based on a set of target templates.)