Remote Sensing Image Sequence Segmentation Based on the Modified Fuzzy C-means

Abstract

Remote sensing image with characteristics of multiple gray level, more informative, fuzzy boundary, complex target structure and so on, there is no completely reliable model to guide the remote sensing image segmentation. In response to these issues, the article presents a remote sensing image sequence segmentation method based on improved FCM (fuzzy c-means) algorithm. The color space selects the lower relevance of HSI (hue, saturation, intensity) and adopts standard covariance matrix-the Mahalanobis distance formula, which is more suitable for the use of remote sensing image. It can solve the initial centers selection problems of fuzzy C-means clustering algorithm by the use of ECM. By using the partition of S component, it can divide the image into high S regions and low S regions. We can do FCM segmentation respectively with H component and I component of these two parts. The segmentation results can be achieved after the merger. The program experimental result shows that this method will enable FCM to converge to global optimal solution with less iteration, and has good stability and robustness. It has good effect on improving the accuracy of threshold segmentation and efficiency for remote sensing images, which can be used for content-based remote sensing image retrieval systems.