Perceptual-based fusion of IR and visual images for human detection

With the cost decline of infrared (IR) cameras, it is envisaged that more IR cameras will be deployed in vision surveillance systems for around-the-clock day and night surveillance. Infrared cameras sense radiation emitted by an object at a non-zero absolute temperature in the infrared spectrum which is not available in a visual image, but lose information, such as texture, color and geometry, which is available in a normal visual camera. The fusion of IR and visual images can enhance features in both kinds of images. And more impressively, it can reveal some new features that might not be present either in IR images or in visual images. In this paper, a simple and yet efficient image fusion scheme, using multiple scales, is developed to implement image fusion for better human detection and surveillance. Since multiple scales are used to represent the image, the possibility of losing image details in the fusion procedure can be greatly reduced. Commercially available images from the Equinox Corporation are also used for testing. Test results show the success and efficiency of the fusion algorithm.