FPGA-based stereo vision system using census transform for autonomous mobile robot

Abstract

This paper presents an FPGA-based stereo vision system using census transform for autonomous mobile robots. Most autonomous mobile robot need to quickly recognize the surroundings in order to avoid obstructions and find pathways. Therefore, faster image processing methods are required to be capable of mobility. Accordingly, the FPGA-based stereo vision system using census transform is proposed, where the feature description represents the adaptation to various environments and has compactness of binary information on logic circuits. As experimental results, the proposed FPGA-based stereo vision system was very faster than the software system on the same platform. Moreover, the mismatch rate was very low for the stereo correspondence.