Moving Object Recognition System Based On FPGA

Moving object detection technology is widely used in biometrics,sun tracking system,public safety,machine vision,UAV tracking and navigation.It is an important branch of video image processing and is the basis for other follow-up tracking recognition algorithms.For the purpose of real-time recognition,FPGA is select as the master chip with the features such as small,low power,speed fast in the thesis.After comparing several moving object detection algorithms,the frame differential algorithm is adopted,for its advantages such as simple algorithm,less data to be processed,easy implementation and so on.The system is composed of image acquisition module and moving object detection module,which is responsible for collecting the current moving object image and detecting the moving target respectively.However,frame differe ntial method usually detects a moving object by using a specific threshold value measured under an invariable lightness condition,which limits its application in variable illumination environment.In this paper,illumination-lightness-threshold table is created based on the lightness in the hue,saturation,lightness(HSL)color space to dynamically adjust the threshold value for different il umination conditions.After simulation with Verilog hardware description language,a detection system has been implemented by FPGA on after Cyclone IV platform.Furthermore,and a measurement experimental setup is built to test the correct rate under different il umination condition,for moving object with different speed.Experimental results show that,the recognition rate reaches 93% and 95% for a moving target with 3.0m/s and 0.5m/s velocity under 90w/m2 illumination by the adaptive method,similarly to the method with a large fixed threshold;under 0.59w/m2 illumination,the recognition rate reaches 84% a nd 92% respectively for the two moving speed above,which is similar to the fixed threshold method with a small threshold value.