A Superpixel-by-Superpixel Clustering Framework for Hyperspectral Change Detection

Hyperspectral image change detection (HSI-CD) is an interesting task in the Earth’s remote sensing community. However, current HSI-CD methods are feeble at detecting subtle changes from bitemporal HSIs, because decision boundary partially stretched by strong so that ignored. In this paper, we propose a superpixel-by-superpixel clustering framework (SSCF), which avoids confusion of different and thus reduces impact on boundaries. Wherein simple linear iterative (SLIC) employed to spatially segment images (DI) HSIs into superpixels. Meanwhile, Gaussian mixture model (GMM) extracts uncertain pixels DI as rough threshold for clustering. The final CD results obtained passing determined superpixels through K-means. experimental two spaceborne datasets demonstrate competitive efficiency accuracy proposed SSCF.