Non-uniform motion blurred image adaptive restoration method based on attention model

Abstract

The invention discloses a non-uniform motion blurred image adaptive restoration method based on an attention model, and belongs to the field of digital image / video signal processing. The invention designs a conditional generative adversarial network combined with an attention mechanism. The generation network is of a coding and decoding structure, in the coding stage, a dense connection network isadopted to extract features, the feature utilization rate is increased, feature propagation is enhanced, and a visual attention mechanism is added, so that the network can adaptively modulate networkparameters and dynamically remove image blurring for different input images. According to the method, the clear image can be effectively restored from the non-uniform motion blurred image. The technology has a wide application prospect in the fields of target tracking, traffic detection, military reconnaissance and the like.

Description

technical field [0001] The invention belongs to the field of digital image / video signal processing, in particular to an attention model-based adaptive restoration method for non-uniform motion blur images. Background technique [0002] Images have become an important way for people to obtain information, and information such as text, logos, and signs in images plays an important role in understanding the scene. However, in the process of image acquisition, due to the influence of factors such as camera shake, image scene depth change, and object movement, the image is often blurred, and the image information is permanently lost due to the irreproducible shooting scene. Working life takes its toll. Although image blur can be reduced by improving the quality of equipment, the equipment is expensive to purchase and there are still many blur problems that are difficult to solve. Therefore, an effective fuzzy image restoration algorithm is of great significance to give full pla...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the existing blur restoration method relying on data-driven and ignoring the lack of scene depth feature information of motion blur images, aiming at the problem of dynamic blind restoration of non-uniform blur images, it provides a motion blur based on attention model Adaptive image restoration network, which can adaptively extract feature weights according to the blur position and the difference in blur degree, capture the blur area and its surrounding structural features, and realize the dynamic deblurring of non-uniform blur images

Images