Quality evaluation method for multi-exposure fusion image simultaneously for dynamic scene and static scene

Abstract

The invention relates to a quality evaluation method for a multi-exposure fusion image simultaneously for a dynamic scene and a static scene. The quality evaluation method is characterized by comprising the steps: firstly dividing a fusion image into a region with a larger information amount and a region with a smaller information amount through employing a superpixel segmentation method based onthe structural difference between the multi-exposure fusion image and a source exposure-level sequence image; secondly, based on a Laplace pyramid, respectively calculating quality maps of regions with relatively large information amount and regions with relatively small information amount; and thirdly, calculating the local quality scores of the regions with large information amount and small information amount by adopting an adaptive weighting strategy based on the information theory, and averaging the obtained local quality scores of the regions with large change and small change to obtainthe quality score of the fused image. Experimental results show that the quality evaluation method shows good prediction performance for visual quality evaluation of multi-exposure fusion images of adynamic scene and a static scene.

Description

technical field [0001] The invention relates to a quality evaluation method for multi-exposure fusion images of dynamic scenes and static scenes at the same time, which belongs to the technical field of multimedia, and specifically belongs to the technical field of digital image and digital video processing. Background technique [0002] With the explosive growth of digital media, people's demand for high-quality images is also increasing. However, the dynamic range of brightness captured by ordinary sensors and displays is limited, and it is difficult to reproduce all the dynamic range in the real world. details. High dynamic range image synthesis technology and multi-exposure fusion technology can overcome this defect. High dynamic range image synthesis technology combines a series of image sequences shot at different exposure levels in the same scene into one high dynamic range image by converting the camera response function , in order to be able to display the image on...

AI Technical Summary

Problems solved by technology

There are only a few objective quality assessment methods for evaluating multi-exposure fusion images of static scenes and a few objective quality assessment methods for evaluating multi-exposure fusion images of dynamic scenes, and none of these methods can simultaneously evaluate multi-exposure fusion images of dynamic scenes and static scenes

As far as the present invention is known, there is no objective quality evaluation algorithm for multi-exposure fusion images of dynamic scenes and static scenes at the same time.

Images