An end-to-end image defogging method based on deep learning

Abstract

The present invention relates to an end-to-end image defogging processing method based on deep learning, which converts a foggy image into a fog-free image through a trained deep convolutional neural network, wherein the deep convolutional neural network includes : Feature extraction module, including multiple convolution sub-modules, performs convolution calculation on input image, extracts multi-dimensional feature map; feature pooling module, includes multiple pooling layers, and each pooling layer is correspondingly connected to one of the volumes After the product sub-module, the multi-dimensional feature map is de-redundantly processed; the recovery module includes a plurality of deconvolution sub-modules, connected after the feature pooling module, and outputs an output image with the same resolution as the input image ; There are multiple inter-layer skip connection layers, which realize the inter-layer skip connection between the output of the pooling layer and the input of the corresponding deconvolution sub-module, and fuse the multi-scale feature map. Compared with the prior art, the invention has the advantages of good defogging effect, simple process and the like.

Description

technical field [0001] The present invention relates to an image processing method, in particular to an end-to-end image defogging processing method based on deep learning. Background technique [0002] Fog is a common atmospheric phenomenon over land and sea. In foggy weather there are many atmospheric microscopic particles of a certain size. They not only absorb the reflected light of the target object / scene, but also their own reflected light enters the camera together with the reflected light of the target object, which interferes with the light information acquired by the camera and makes it impossible to clearly image the target object / scene. Due to the blur and noise of imaging, it brings great difficulties and challenges to the performance of various algorithms based on computer vision, such as target recognition / tracking, scene segmentation, automatic driving, etc. [0003] With the development of image processing technology, image dehazing has received extensive ...

AI Technical Summary

Problems solved by technology

[0004] At present, the traditional image defogging processing methods have great deficiencies in the restoration accuracy and universality, and most of the existing deep learning-based methods have not achieved effective end-to-end image defogging, and need to pass the estimated transmittance and Atmospheric light intensity for postprocessing

Images