Research Of Moving Object Detection And Tracking Techniques On Intelligent Video Surveillance System And DSP Implementation

Video surveillance system has been widely used in the fields of security control, intelligent traffic system, intelligent weapons, and so on. It is very important in many sides of society. In order to solve the inadequacies of exited system that can not guarantee the accuracy and real-time processing, this dissertation discussed and studied the key technology of moving object detection and tracking on video surveillance systems ,as well as the DSP implementation of this algorithms.On the research of moving object detection, by studying and analyzing a great number of methods, in this dissertation, an improved background subtraction algorithm based on gaussian model has been proposed, and a hybrid detection framework by combining gaussian model and frame differencing algorithm has been presented; in addition, from the point of statistics, this dissertation uses a non-parametric technique of triangle kernel estimation, which overcomes the shortcoming of parametric technique that relies on model specifications, to model the scene background, and presents a updating method to adapt to changes in the scene after detecting foreground object. It has been proved in the experiments that this algorithm can achieve higher sensitivity and more robust detection result. On the research of object tracking, by studying several related algorithm, this dissertation improves the extend Kalman filter to tracking targets which make use of the detection results and compare centroid position and area instead of complicated template matching, thus this method improve the tracking speed, as well as handling the cluttered scene with a simplicity and efficient approach. Following, in this dissertation, a whole intelligent video surveillance system software framework which can saving video storage and auto-alarm is designed. Last, on the research of the characteristics and the software development of TI TMS320C6000 series DSP, this dissertation transplant and optimize the coding in DSP, and project is executed successfully on CCS simulator.