干旱区生态环境知识资源中心

Infrared polarization imaging detection can be used to obtain not only the polarization state but also the radiation of target. With this method, the target that traditional photometry cannot detect can be settled. The degree and angle of polarization that used in polarization detection reflect different physical properties, and it is seriously redundancy along with intensity of images. A target detection method for polarization infrared image in the background of desert is proposed in allusion to the character. A modified kernel fuzzy clustering algorithm is purposed to cluster infrared images and the polarization images. Then to distinguish target from the background, the object information of clustered infrared and polarization image were combined according to sparse fusion method. Experimental results show that the proposed detection method is lower noise and more clearly details than wavelet fusion and laplacian pyramid fusion.