Multi-level feature fused generative adversarial network image defogging method

Abstract

The invention relates to a generative adversarial network image defogging method fusing multi-level features. The method is based on an end-to-end defogging algorithm of deep learning, during down-sampling, feature extraction is carried out on foggy images with different resolutions, the extracted different feature maps are learned through an SE-ResNet module, information between channels is better fitted, and performance degradation caused by network deepening is prevented. And splicing the learned multi-level feature maps, and fusing more image features. And then, during up-sampling, putting a feature map after down-sampling fusion into an SE module for learning so as to better distribute channel weights and enhance useful features. And splicing the learned feature map with the up-sampling feature map, and fusing more image information. And finally, adding the residual image of network learning and an input foggy image to obtain a final image defogging result. Experimental results show that the image defogging method provided by the invention is better in defogging performance.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a generative adversarial network image defogging method that integrates multi-level features. Background technique [0002] In foggy weather, the irradiance received by the camera from the scene attenuates along the line of sight, and the turbid medium in the atmosphere will absorb the light of the scene image, causing the captured image to lose contrast and color fidelity, reducing the quality of the image, and directly affecting Tasks such as video surveillance, remote sensing images, automatic navigation and target recognition. Therefore, by designing an algorithm model to eliminate the adverse effects of haze factors in the image, and restore the foggy image to a clear image, people can obtain more information they need from the image. Existing image defogging algorithms are mainly divided into two categories, namely, traditional image defogging methods ...

AI Technical Summary

Problems solved by technology

[0003] The classic traditional defogging method is mainly based on the construction of the atmospheric scattering model to obtain the defogged image, but the overall color of the defogged image is dark and the image edge is easily distorted, or the sky area in the image is prone to failure and heavy calculation

Due to the obvious human interference factors in the calculation of parameters by the traditional method, the dehazing effect is not ideal. In recent years, the dehazing method based on deep learning has begun to rise.

Images