Remote Sensing Image Segmentation Based on a Novel Gaussian Mixture Model and SURF Algorithm

This paper proposes a novel remote sensing image segmentation method based on Gaussian mixture model and SURF algorithm. Firstly, is used for segmentation. Then the surf matching algorithm adopted eliminating misidentified areas. The determinant of Hession matrix (DoH) to detect key points in image. non-maximum suppression interpolation operation are utilized search locate extreme points. maximum likelihood estimate parameters. Some images THE DOTA data set selected experimental verification, results show that new has obvious improvement effect efficiency. In background complex segmentation, improved more advantages compared than state-of-the-art methods.