Quality blind evaluation method for unmanned aerial vehicle image

Abstract

The present invention relates to a quality blind evaluation method for an unmanned aerial vehicle image. The method comprises the steps: S1, obtaining an unmanned aerial vehicle image, and performing analysis at three aspects of the image information structure character, the image information integrity and the image information color character; constructing the corresponding quality evaluation measurement; and constructing a standard MVG model by employing a multi-Gaussian beam model, and finally obtaining the quality equal division of the whole image by employing a mean value method. On the basis of comprehensively analyzing the classic no-reference image quality evaluation method and unmanned aerial vehicle image features, aiming at the unmanned aerial vehicle image multi-distortion and mixture problem, the quality blind evaluation method for an unmanned aerial vehicle image extracts three types of quality feature factor sets capable of showing the unmanned aerial vehicle image multi-distortion scenes for perception expression for three types of main distortion of information entropy integrity, structure information changing and color loss.

Description

technical field [0001] The invention relates to the technical field of image quality assessment, in particular to a blind quality assessment method for drone images. Background technique [0002] The UAV image is a long-distance, non-contact imaged image through the UAV high-altitude platform. With the continuous development of imaging technology, the resolution of images taken by drones is getting higher and higher. People process the information of targets in drone images to obtain qualitative or quantitative descriptions of targets. The result after imaging—the quality of UAV images has attracted the attention of image workers at home and abroad. [0003] However, there is no mature set of quality evaluation criteria for drone images. The quality evaluation of UAV images often adopts the traditional observation method, that is, the quality of the image is judged by viewing the image with human eyes. This approach involves a large number of subjective factors. Therefor...

AI Technical Summary

Problems solved by technology

However, a thorough assessment is still lacking

[0012] 3. IQA algorithm for non-specific distortion types

[0020] 2. Over-threshold distortion and degradation processing problem;

[0022] 4. Evaluation of multi-distortion hybrid, geometric deformation and enhancement processing;

Images