A comparison of image fusion methods on visible, thermal and multi-focus images for surveillance applications

Because of rapid development in sensor technology in recent years, machine perception for security purposes can be improved by using different sensor types. Fusing of images from different sensors is the key point of this development. In this paper, seven well-known image fusion methods are compared visually and quantitatively on three surveillance applications including enhanced night vision, concealed weapon detection and extending depth of the field of an optical camera.