基于DSPs的运动目标检测与匹配

建立了一个基于TMS320C6701的DSPs系统,实现复杂背景中单个运动目标的实时跟踪.同时给出在复杂背景下人物自适应跟踪的实验结果.在这基础上,结合运动目标检测技术和模板匹配法,讨论一个复杂背景下多运动目标自适应跟踪系统,同时也给出运动目标检测和模板匹配的实验性结果.

A moving object dection and match based on DSPs

This paper describes a real time moving object tracking system at the beginning, sets up a DSPs based on the TMS320C6701. First, the DSP board calculates optical flows (the velocity field of an image) based on the gradient method. Next, the region of the moving object on the image is extracted from the optical flows using knowledge about the region of the object, such as Region-Merge arithmetic, Region-Connection arithmetic or Clustering arithmetic. Finally, the camera is controlled to keep the object in its field of vision. Therefore achieves a real time system to track the moving object in the multiple scenes. The result of experiments shows that the method can track the moving person in the multiple backgrounds in real time. And then the paper combines the goal detection technique of the movement and template matching on the basis of this to discuss at length the adaptive tracking system of multi-target under the complicated background, and gives some experimental results of the moving object detection and template matching at the same time.