A Novel Algorithm for Edge Detection of Remote Sensing Image Based on CNN and PSO

With the development and applications of satellite remote sensing technology, the edge detection accuracy of remote sensing image is increasingly high. It is difficult to extract an excellent edge from remote sensing image using traditional method because of the turbulence by earth atmosphere and ground resolution of the sensor. In this paper, a novel edge detection method based on cellular neural network (CNN) is presented. In order to get the reasonable template, particle swarm optimization (PSO) is utilized to search the optimal one. The experimental results show that, compared with the traditional edge detection algorithms of Sobel operator and LOG operator, the proposed edge detection method produces excellent results which are more complete and realistic.