Single-Image Dehazing Based on Two-Stream Convolutional Neural Network

Abstract

The haze weather environment leads to the deterioration of the visual effect of the image, and it is difficult to carry out the work of the advanced vision task. Therefore, dehazing the haze image is an important step before the execution of the advanced vision task. Traditional dehazing algorithms achieve image dehazing by improving image brightness and contrast or constructing artificial priors such as color attenuation priors and dark channel priors. However, the effect is unstable when dealing with complex scenes. In the method based on convolutional neural network, the image dehazing network of the encoding and decoding structure does not consider the difference before and after the dehazing image, and the image spatial information is lost in the encoding stage. In order to overcome these problems, this paper proposes a novel end-to-end two-stream convolutional neural network for single-image dehazing. The network model is composed of a spatial information feature stream and a high- level semantic feature stream. The spatial information feature stream retains the detailed information of the dehazing image, and the high-level semantic feature stream extracts the multi-scale structural features of the dehazing image. A spatial information auxiliary module is designed and placed between the feature streams. This module uses the attention mechanism to construct a unified expression of different types of information and realizes the gradual restoration of the clear image with the semantic information auxiliary spatial information in the dehazing network. A parallel residual twicing module is proposed, which performs dehazing on the difference information of features at different stages to improve the model’s ability to discriminate haze images. The peak signal-to-noise ratio (PSNR) and structural similarity are used to quantitatively evaluate the similarity between the dehazing results of each algorithm and the original image. The structure similarity and PSNR of the method in this paper reached 0.852 and 17.557dB on the HazeRD dataset, which were higher than existing comparison algorithms. On the SOTS dataset, the indicators are 0.955 and 27.348dB, which are sub-optimal results. In experiments with real haze images, this method can also achieve excellent visual restoration effects. The experimental results show that the model proposed in this paper can restore desired visual effects without fog images, and it also has good generalization performance in real haze scenes.