Image Dehazing Algorithm Based On Improved Guided Filtering
Jin Lin, Junjie Yang, Ting Yu, Chuanping Geng · IOP Conference Series Earth and Environmental Science · 2020
Abstract Aiming at the problem that the image defogging algorithm based on the dark channel prior will cause the edge halo effect in the restored image, an image defogging algorithm based on improved guided filtering is proposed. First, the calculation method of atmospheric light value based on the quadtree algorithm is adopted to obtain a more accurate atmospheric light value; then, the edge weight factor based on the Canny operator is added to the guided filtering algorithm to solve the local halo effect; finally, the image is restored based on the atmospheric physical model. Experiments show that this algorithm is better than other algorithms in subjective visual effects, and the image edge defogging is more natural; the comparison of objective performance indicators shows that the improved defogging algorithm has higher image quality and better image restoration.