Single image fine rain removal method based on depth convolutional neural network

Abstract

The invention discloses a single image fine rain removal method based on a depth convolutional neural network. Firstly, through carrying out background texture structure extraction, nonlinear mapping and rain line area restoration on an inputted rain graph by an initial rain removal network, an initial clear rain-free image is finally obtained; the initial clear rain-free image and the original image are inputted to a fine rain removal network with a single convolutional layer at the same time, more details in the background area are thus restored, and a high-definition rain removal image is finally obtained. Through adopting a caffe framework, the initial rain removal network and the fine rain removal network are trained, parameters of each convolutional layer are obtained precisely, fine rain removal processing is carried out on a rain image, and compared with the traditional convolutional neural network rain removal method, the method of the invention can obtain a higher-quality rain-free image, the practicability is strong, and the method can be widely applied to more scenes.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for finely removing rain from a single image based on a deep convolutional neural network. Background technique [0002] Image deraining is an important module of computer vision systems, especially for image-based decision-making applications, such as security surveillance and robot navigation, image deraining is an important preprocessing step, even when images are taken in extreme rainy environments, it is expected Restores the visual details of the target object in the rainmap. [0003] Although many methods have been proposed for video denoising in the past decade, they cannot be directly extended to the single image denoising problem due to the unavailability of dynamic visual and temporal cues. [0004] Recently, significant progress has been made in the single image deraining problem, among which, Kang et al. proposed a method to detect and separate the ...

AI Technical Summary

Problems solved by technology

[0003] Although many methods have been proposed for video denoising in the past decade, they cannot be directly extended to the single image denoising problem due to the unavailability of dynamic visual and temporal cues.

[0004] Recently, significant progress has been made in the single image deraining problem, among which, Kang et al. proposed a method to detect and separate the rain component by dictionary learning and sparse coding, which achieved good results, but it cannot deal with complex background information. The rain image; the most representative Luo et al. based on the nonlinear layer mixture model, can restore the rain layer of the image through discriminative sparse coding to derain the result, but it tends to blur the background of the image; similar problems are also in Appeared in the method of Li et al., Li et al. constructed a Gaussian mixture model (GMM) based on the prior information of the rain line, and then removed the rain line and restored the background. These existing image solving methods turn the rain graph into a linear model , and recover rain layers with different characteristics or priors, however, this method cannot be adapted to real scenes because the physical influence of rain on images is usually complex

Images