Improved dynamic image fusion scheme for infrared and visible sequence based on image fusion system

Improved dynamic image fusion scheme for infrared and visible sequence based on image fusion system is introduced in this paper. Target detection technique is employed to segment the source images into target and background regions as the first step of the improved dynamic image fusion for infrared and visible sequence. Different fusion rules are adopted respectively in target and background regions. Two quantitative performance indexes are feedback to determine optimum weight coefficients for fusion rules. This feedback performance information improved the fusion result and effectiveness in target regions. Fusion experiments on real world image sequences indicate that the improved method is effective and efficient, which achieves better performance than those fusion methods without feedback.