Multi-band high-resolution remote sensing image segmentation method based on gray scale co-occurrence matrix

Abstract

The invention discloses a multi-band high-resolution remote sensing image segmentation method based on a gray scale co-occurrence matrix. In texture images based on the gray scale co-occurrence matrix, precipitation watershed transformation is adopted for segmentation of each band image, and therefore band segmentation results are superposed. At last, a region merging strategy based on multi-band spectral information is provided for merging fragment regions in the segmentation results, and finally image segmentation is achieve. A high-resolution ALOS image and an SPOT 5 image are tested respectively through the method which is compared with a traditional segmentation method based on local area homogeneity gradients. As is shown in experimental results, edges of an object can be accurately positioned, over-segmentation and under-segmentation are effectively overcome, and higher segmentation accuracy and stability are achieved.

Description

technical field [0001] The invention relates to a multi-band high-resolution remote sensing image segmentation method based on a gray level co-occurrence matrix, and belongs to the technical field of remote sensing image segmentation. Background technique [0002] At present, high-resolution remote sensing images are widely used in many fields such as urban planning, environmental assessment, and military affairs, and object-oriented analysis methods are receiving more and more attention in the research of high-resolution remote sensing images. Effective image segmentation is the foundation and important guarantee of object-oriented analysis methods. At present, the segmentation methods of high-resolution remote sensing images are mainly divided into five categories: segmentation methods based on pixels, such as threshold method and clustering method; segmentation methods based on edge detection; segmentation methods based on regions; segmentation methods based on physical m...

AI Technical Summary

Problems solved by technology

On this basis, Chen Qiuxiao et al. proposed a novel high-resolution remote sensing image segmentation method based on local homogeneity gradients. This algorithm effectively solves the over-segmentation problem of watershed transform, but there are also the following problems: Too rough quantization leads to the serious loss of a large amount of detailed information in high-resolution remote sensing images, which is prone to under-segmentation, and it is difficult to accurately locate the edges of objects; because there are a large number of objects with similar gradient characteristics in high-resolution remote sensing object, and this method only uses gradient information as the basis for extracting objects, so more feature information needs to be introduced to distinguish these objects; finally, the region merging strategy adopted by this method only uses the gray level of the object in the gradient image The information is compared, while ignoring the spectral differences of different objects in different band images in high-resolution remote sensing images, which may cause false merging

Images