Navigation and surveillance using night vision and image fusion

Abstract

In this paper, an efficient algorithm for integrating infrared information into images with natural appearance is proposed. The obtained result can be used for different navigation and surveillance applications. The proposed algorithm uses the characteristics of human visual system in framelet domain. The main idea is to decompose the natural and IR images to be fused into low and high frequency bands using framelet transform. The fusion is performed by two different strategies while exploiting the characteristics of low and high frequency bands. The first strategy is adaptive weighted average based on local energy and is applied to fuse the low-frequency bands. In order to fuse high frequency bands, a new strategy is developed based on texture while exploiting the human visual system characteristics, which can preserve more details from source images and further improve the quality of scene in the fused image. Experimental results demonstrate the efficiency and robustness of the proposed algorithm in visual inspection and objective evaluation criteria.