Fusion of Infrared and Visible Images for Surveillance Applications using Ann

Abstract

Edge preserving filters were used to Multi-Scale Decomposition (MSD) for fusion of visible and infrared images. Traditional edge preserving MSDs may be unable to achieve satisfactory structural separation from details, resulting in fusion performance degradation. The objective of this work is to propose a MSD Iteration with ANN fusion technique for infrared and visual image which improves the fusion execution. Initially the original image is decomposed by “Gaussian smoothness and joint bilateral filter”. Edge retention and scaling perception attributes are introduced to satisfactorily separate image details from source images. Decomposition includes preserving the attributes of edge and zoom perception, so that the detail information is completely separated from the image details and the improvement of fusion performance is maintained. The rule aims to merge these decomposed layers. A saliency map is constructed by Laplacian and Gaussian low-pass filters to find the initial weight map and further a guided filter is used to determine the final weight map. The enhanced fused image later obtained by using ANN, which eventually increases the act of fusion execution. This work proposes ANN based fusion algorithm for fusing visible and infrared images and obtains better performance by reducing the complexity.