Design And Realization Of Intelligent Video Surveillance System Based On FPGA

For the past few years,Along with the digital image processing technology unceasing development and improving,make video monitoring by the people more and more attention.As the mainstream of large-scale programmable application-specific integrated circuit, FPGA can satisfy the need of high-speed image processing. It can make more hardware resources, faster processing and better flexibility to use the FPGA design.This paper propose the intelligent video monitoring system based on FPGA. The system uses DE2development board of Altera as the hardware platform. CMOS image sensor monitors the environment in real time. The VGA monitor displays the image getting from CMOS image sensor. When there is moving objects in the environment, then the system will send the alarming signal to notify the monitoring staff by the headphones and the LED of DE2development board. The number of the red LED shows the degree of velocity.The system is achieved in a synergistic manner of software and hardware. Hardware: first, on the basis of the requirement analysis, the paper designs and implements four modules: image capture module, SDRAM(Synchronous Dynamic RAM) module, image display module and moving objects detection algorith module. In the moving objects detection algorith module, Using the SOPC builder in Quartus II to construct the sopc_system module for the basis of analysis algorithm behind.Due to the edge area accumulated value absolute difference algorithm resources share is lower,the system can funny operation.Software:First studied W4algorithm and carries on the improvement, use of each frame of the test results to guide the background model, and then simulation the improvement W4algorithm in the MATLAB, update the effect of the improved algorithm, and finally the algorithm to realize the FPGA transplantation, the algorithms are programmed and debugged by C language in the Nios II IDE environment.According to the test, the system recognition rate above90%,has the very good video detection effect.