Segmentation of high-resolution remotely sensed imagery combining spectral similarity with phase congruency

A modified algorithm of marker鄄based watershed segmentation was proposed by combining spectral similarity with phase congruency model in this paper. The performance of segmentation using marker鄄based watershed algorithm was decided by the result of edge detection from remotely sensed imagery. Thus we use spectral similarity of the same type ground object from remotely sensed imagery to suppress fake edges and noises to retrieve good segmentation results. In this paper, a spectral similarity model defined by the sum of distance of spectral curve between the target pixel and ad鄄 jacent pixels was introduced into phase congruency model for edge detection. Then segmentation of remotely sensed im鄄 agery was obtained by using auto marker鄄based watershed algorithm. Finally, an unsupervised evaluation and comparison of the image segmentation from the proposed algorithm and some other existing algorithms was implemented using infor鄄 mation entropy. Furthermore, the computation time of the proposed algorithm was also compared with other algorithms. The experimental segmentation results show that the proposed algorithm can reduce the over鄄segmentation phenomenon efficiently and it is readily to obtain better segmentation results by using this algorithm.