A New Video Image Edge Detection Approach

Edge detection is an important pretreatment process in image processing and computer vision. But it is still a challenge on how to get edge information efficiently in video image processing. In this paper, firstly, we analyze several traditional operators and then suggest an improved operator based on Isotropic Sobel operator. Secondly, in order to get a better performance in video image processing, we suggest a new video image edge detecting approach which combines DSP/BIOS and the improved operator based on DM642. The experimental results show that the new approach remains advantages of traditional operators, meanwhile, it can reduce the effect of objects' moving and has a fine detecting effect in video image processing.