A FPGA real-time stereo vision system with luminance control and projected pattern

This paper presents a real-time stereo video processing system based on FPGA. The system takes rectification and histogram equalization as its pre-processing, and the depth detection of this system is using generalized census transform and block matching method. With the help of on-line generated projected pattern by the pattern controller inside FPGA, this system can be used in various environments. The median filter is used as the post-processing step of depth map. In comparison to the software solution method, this system takes the advantage of the parallel nature of FPGA and got higher speed in generating the depth map. Therefore, it can be applied to the applications demanded for better performance.