Research On Pointer Image Recognition Based On ARM Embedded Video Monitoring System

In electric system, the instruments with a pointer have been widely used. Whether they are safely running play an important part for the safe operation of the entire power system. This thesis has realized recognizing pointer angle automatically based on ARM embedded video surveillance system. First, the paper briefly introduces the general framework of system, including hardware design and software design. The hardware part uses S3C2410 processor with ARM920T core and complete the function of memory,interface circui,image input part and arm-linux-gcc. The software part uses many image processing technology, such as graying,image de-noising,enhancement binary image and edge detect, processes the collected images and recognizes the pointer angle by Hough processing. The experimental results show that the proposed algorithms are simple and easy to achieve, and have a good recognizing result. At last the conclusions are given with recommendation for future work.