Real-time target tracking and positioning on FPGA

Abstract

Recently, FPGA becomes more important and popular in embedded systems due to its parallelizable inner structures. In this paper, a pipelined FPGA architecture will be present which will be used on a mobile robot. It implements algorithms about target recognition, tracking, positioning based on monocular vision, etc. The hardware platform for the design is the development board by Xilinx. The system uses monocular camera to measure the orientation of target in real time. It acquires the video stream from CMOS camera. The system realizes target tracking by extracting the color of the target as the feature, filtering, detecting feature of the target and then displaying on the screen. The system realizes target positioning according to the centroid of the tracked target, then computing the orientation which can be used for the intelligent robot vision.