Research On Image Restoration Algorithm Based On Atmospheric Scattering Model

In recent years,the rapid development of artificial intelligence technology has not only changed people’s production,lifestyle and way of thinking,but also effectively promoted the pace of social and economic development.As an important part of artificial intelligence,computer vision realizes information processing by using computers and related equipment to simulate biological vision,and has been widely used in intelligent transportation,face recognition,medical image analysis and other fields.However,the medium particles suspended in the air will scatter and absorb light under hazy conditions,resulting in degradation of the captured outdoor images such as contrast loss and color distortion.Which has a great impact on advanced computer vision tasks such as outdoor object recognition,obstacle detection,and video surveillance.Therefore,it is of great research significance and practical application value to study a simple and efficient image dehazing algorithm which can make degraded image clear,so as to ensure the stable operation of the computer vision system.This paper analyzes the existing traditional restoration algorithms and deep learning algorithms,and summarizes the advantages and disadvantages of this algorithms.Then,two improved algorithms are proposed based on the atmospheric scattering model,which have achieved good dehazing effect.The specific research work is as follows:Aiming at the problems such as halo effect and color cast of sky area in dark channel prior algorithm,an image dehazing algorithm based on transform domain and adaptive gamma correction is proposed.By transforming atmospheric scattering model to logarithmic domain,combined with the dark channel prior theory,a positive correlation in logarithmic domain is proposed.Then the Gaussian function is used to fit positive correlation to obtain the coarse transmission.At the same time,the hazy image is converted to HSV color space,the brightness component is extracted to construct an adaptive gamma correction factor,the coarse transmission is corrected.And cross bilateral filtering operation is used to further optimize the trans-mission.Finally,the restoration of the haze-free image is realized by atmospheric scattering model and im-proved local atmospheric light.Experimental results show that the restored image has rich details and thorough degree of dehazing.Moreover,it is closer to the real scene because of the better color fidelity.Aiming at the problems such as color distortion and incomplete haze removal in dehazing algorithms,a multi-level feature fusion network based on the learning of hazy layers is proposed for single image dehazing.Firstly,the difference image between hazy image and haze-free image is defined as the hazy layer via the atmospheric scattering model,and the optimal dehazing effect is achieved through effective estimation of the hazy layer.Then,an end-to-end network model is designed,which mainly includes a hazy layer estimation module and an image restoration module.In the hazy layer estimation module,the low-level and high-level features of the image are extracted through feature extraction blocks,and the multi-level fusion strategy is used to add the features of different levels pixel by pixel to achieve feature fusion.The fused hazy layer contains both local and global information.Finally,the hazy layer is directly subtracted from hazy image to achieve the effective restoration of haze-free image according to the image restoration module.Experiments show that the proposed algorithm can obtain clear and natural results,and the color distortion phenomenon is effectively avoided.The objective evaluation indicators further verify the effectiveness of the proposed algorithm.