Study Of A System For Automatically Detecting And Tracking The Moving Object Based On DSP

The thesis is focused on the study of the system of moving object detection and tracking based on DSP, including the design of the hardware platform and the algorithm software module for moving object detecting and tracking.Against the limitation found in the investigation for the current status of the surveillance and control system, a new system of moving object detection and tracking based on DSP is studied. This paper adopts the TMS320C6416 DSP produced by TI company as the primary control chip to design a hardware platform and the debugging result are gained. The moving detection and tracking are task-dependent. According to different application, the corresponding algorithm will be selected. In the thesis, the advantage and shortcoming of some algorithms are analyzed and compared firstly, and according to the characteristic of video images and the requirements of real-time for the system, the method of the optical flow field estimation based on grads combined with image difference is established as the pivotal algorithm. Most software module programs are compiled with the language C, and the execution time of the program is debugged and the real-time performance compared as well. The system resolves the problem of the conversion of the coordinates through demarcating the coordinates. The dome camera is controlled according to the control protocol of it to track the centroid of the moving object.Seeing from the experiment result and data throughout the paper, the moving object can be exactly and timely detected and tracked by the system under the specified case and it can attain to the expected effect basically.