Target detection in thermal-visible surveillance based on multiple-valued immune network

Two fuzzy adaptive resonance neural networks were utilized to build the background models of thermal and visible components. According to the multiple-valued immune network model, a series of immune response strategies were designed to cooperate B cell with T cell to build the interactive model, which takes the infrared background model as B cell and the visible background model as T cell. With the interactive model, the targets are detected according to the degree of fuzzy match between pixels and models. Experimental results show that the F1 measurement of the proposed approach is up to 96.4%. It is able to complement information between thermal and visible components effectively. The method is capable of detecting targets in complex scenes effectively.