Segmentation of high-resolution remote sensing image combining phase congruency with local homogeneity

Realizing both of the effective weak edge detection and fake edge suppression is an extremely challenging problem facing high-resolution remote sensing (HRRS) image segmentation. To address the problem, an HRRS image segmentation method combining phase congruency with local homogeneity is proposed by advantageous complementarities. Firstly, the Log Gabor Filter is used to extract phase congruency information. Then, the local homogeneity index J value is adopted to optimize the edge detection results. On this basis, an objective function optimization strategy based on minimizing inter-scale mutual information is proposed, and a parameter-adaptive model of edge response is established. In the end, the segmentation results are obtained by multi-scale region segmentation and merging based on this model. Two sets of HRRS images are used in experiments, and the results are compared with the J value-/phase congruency-based models, the well-known commercial software e-Cognition, and a traditional gradient-based segmentation method, respectively. Both visual and quantitative evaluations have demonstrated the effectiveness of the proposed method.