Infared Target Extraction in FLIR Imagery Based on Spatio Temporal Using Fuzzy Clustering

A novel fuzzy clustering based target extraction algorithm for FLIR imagery using spatio-temporal technique is presented. Firstly, in temporal domain, we establish the Gauss distribution model of frame difference background by incorporating the motion information of the target. And then, the infrared target region is determined based on change detection mask. Secondly, in spatio domain, the improved fuzzy clustering algorithm is proposed by modifying the fuzzy membership function. The spatial relation matrix between pixel and region is constructed to constrain this function. The region which contains the entire target is segmented efficiently based on the improved fuzzy clustering algorithm. At last, infrared target extraction is achieved by the fusion of spatio and temporal results. Experimental results show that the proposed algorithm is simple and effective which can facilitate the target recognition and tracking in the next step.