A Novel Remote Sensing Image Change Detection Algorithm based on Game Theory Analysis and Hierarchical Fuzzy Clustering

摘要

A novel remote sensing image change detection algorithm based on game theory analysis and hierarchical fuzzy clustering is proposed in this paper. This technique integrates the Nash game theory framework and the hierarchical structured clustering approach. Characteristics of the image restoration and segmentation are analyzed to serve as the pre-processing step with the optimal tactical balance. With the deepening of the hierarchy, distributed clusters inside tightness degree gets less, at the same level of processing conforms to close conditions in current layer with sub-manifold merge, therefore, we choose hierarchical fuzzy clustering to finalize the change detection task. Experimental result confirms the effectiveness and feasibility of the proposed methodology. It increases the overall accuracy and robustness of the change detection processes compared with other approaches.