A fusion method and a fusion system of high dynamic range images

Abstract

The invention relates to a fusion method and a fusion system of high dynamic range images. The method comprises the following steps of: performing target detection on each LDR image in a low dynamic range image sequence to obtain an initial detection frame, expanding the initial detection frame according to a preset proportion, extracting a region to be segmented in an alternative detection framefrom the LDR image, and segmenting the region to be segmented to obtain a segmented target; The moving state of the segmented object is judged, and the moving object is merged into a background imageto obtain the segmented image of the moving object. Pixel clustering is performed on the LDR image with the highest exposure quality, a super pixel segmentation image is acquired, and the moving object segmentation image and each LDR image are weighted and fused according to the number of pixels of each super pixel mapped on the moving object in the moving object segmentation image to obtain a high dynamic range image. The invention improves the accuracy of moving object detection and judgment, and makes the moving object in the high dynamic range image clearer.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a high dynamic range image fusion method and fusion system. Background technique [0002] High dynamic range HDR images can be obtained by fusing LDR sequences of low dynamic range images shot in the same scene, which are well consistent with the real details seen by the human eye in the scene, and are used for games, movies, cameras, etc. Many fields. Due to the presence of uncertain moving objects and motion information in this scene, "ghosting" or blurring occurs in the HDR image, which seriously reduces the image quality. [0003] In related technologies, in order to eliminate the "ghost" or blurring phenomenon in HDR images, two methods are mainly adopted: one way is to improve the internal hardware structure of the camera to capture the HDR images in the aforementioned scene in a relatively short period of time. This method greatly increases the cost of the camer...

AI Technical Summary

Problems solved by technology

[0006] However, the above method of optimizing the fusion algorithm is still based on the fusion of multiple LDR images at the pixel or block level to obtain an HDR image, which lacks consideration of the structure of moving objects, and will miss smaller moving objects or detect the motion state of larger moving objects incorrectly. precise

Images