abstract |
The invention relates to the technical field of artificial intelligence, in particular to a multi-exposure image fusion method and system based on artificial intelligence, including: obtaining a principal component weight map corresponding to each image, adaptive Exposure weight map and saliency weight map, and finally fuse N images with different exposure degrees according to N images with different exposure degrees and the principal component weight map, adaptive exposure weight map and saliency weight map corresponding to each image , which generates an HDR image. The present invention characterizes the weights of images with different exposure degrees during fusion through the principal component weight map, the adaptive exposure weight map and the saliency weight map, and can determine the weights during fusion for the adaptability of images with different exposure degrees, thereby improving the performance of the image. The quality of the final fused HDR image. |