INFRARED AND VISIBLE LIGHT FUSION METHOD BASED ON SALIENCY MAP ENHANCEMENT

摘要

The present invention belongs to the field of image processing and computer vision. Provided is an infrared and visible light fusion method based on saliency map enhancement, which is an infrared and visible light fusion algorithm using a filtering decomposition means and saliency enhancement. The method comprises: using a binocular camera and NVIDIA TX2 to construct a high-performance computing platform, and constructing a high-performance solving algorithm to obtain a high-quality infrared and visible light fused image. A system is easily constructed, and acquisition of input data can be completed by using a stereoscopic binocular infrared camera and a visible light camera respectively; a program is simple and is easily implemented; different imaging principles of infrared and visible light cameras are used; an input image is decomposed into a background layer and a detail layer by means of filtering decomposition; a fusion method based on saliency map enhancement is designed for the background layer, and a fusion algorithm based on pixel contrast is designed for the detail layer, and the algorithm effectively enhances the quality of a fused image and processes artifacts generated after image fusion; and finally real-time performance is achieved by means of GPU acceleration.