Open AccessSLIC segmentation method for full‐polarised remote‐sensing image
Author(s) -
Zhang Zhanyang,
Chen Jiaqi,
Liu Zhiwei
Publication year - 2019
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2019.0337
Subject(s) - computer science , artificial intelligence , remote sensing , computer vision , pixel , segmentation , image segmentation , image (mathematics) , feature (linguistics) , image resolution , pattern recognition (psychology) , geology , linguistics , philosophy
The rapid development of remote‐sensing data acquisition technology means that the resolution of remote‐sensing image has been continuously improved, resulting in the large scale of remote‐sensing image data and the increase of redundant information, which restricts the image processing and analysis. However, super‐pixel segmentation method mainly aimed at the general image segmentation algorithm, rarely for remote‐sensing image. Therefore, here, the polarisation decomposition of full‐polarised remote‐sensing images is used to synthesise pseudo‐colour images. Then, based on the region, the image segmentation algorithm based on the colour feature of SLIC super‐pixel segmentation algorithm is used to make it have important application value in remote‐sensing image target extraction. Here, the image of Danjiangkou reservoir obtained by high‐resolution space‐borne SAR is selected as the research object. Finally, the polarisation decomposition and segmentation of full‐polarised remote‐sensing images are realised, and the advantages of SLIC super‐pixel algorithm are proved.