Research on Local Image Navigation Method for Visual-Impaired Person

Due to no navigation in small area of the existing navigation system, we proposed an image-based matching navigation system for people with disabilities can walk in the designated area. Firstly, acquire and process the image captured from specified area by CCD digital video camera to establish Benchmark Image Library. And then pre-process the real-time image captured in walking to get Real-time Image Library. To match benchmark image with real-time image by fast scene matching algorithm based on SIFT feature. After that, match feature points for image that maybe rotation or change in scaling in different lighting and camera angles. Experimental results show that performance of the algorithm meet the requirements of high-performance of scene matching navigation systems.