Infrared and Visible Image Fusion based on Saliency Detection and Infrared Target Segment

Abstract

Infrared and visible image fusion is significant to the overall detection and tracking performance of a video surveillance system. Considering the characteristics of infrared and visible images, the ideal fusion of the infrared and visual image should integrate the bright features of the infrared image, while preserving a considerable amount of background information of the visible image. However, current methods use inadequate information extraction. An efficient infrared and visible image fusion method is thus proposed in this paper based on saliency detection and infrared target segmentation. Firstly, an image descriptor, referred to as an image signature, is introduced. The saliency algorithm is implemented to obtain the infrared image region of interest. Secondly, an infrared target is segmented from the region of interest by adopting a thresholding method. Subsequently, the infrared target is added to the image, which is fused from the original infrared and visible image by known image fusion methods. The most remarkable advantage of the proposed method is that it can obtain a clear infrared target. To verify the proposed method, it was experimentally compared with several classic fusion algorithms. By subjectively comparing the fused results, it was demonstrated that the proposed method not only extracted the important infrared targets, but it also showed good visual quality retained in the background information.