An optimized image fusion algorithm for night-time surveillance and navigation

Multi-sensor Image fusion has its effective utilization for night-time surveillance and navigation. It provides a way to merge multi-sensor nighttime imagery by combining the outputs of different imaging sensors. In this paper, we present an optimized image fusion approach comprising Structural Similarity, Principle Component Analysis and Discrete Wavelet Transform. The use of structural similarity is proposed for adjusting the quality of finally fused image. Recently developed objective image fusion qualify evaluation technique, image quality index, is used to evaluate the performance of our fusion algorithm. Experimental results show that it performs considerably well across a variety of multi-source nighttime imaging data.