Image Dehazing Algorithm based on Morphological and Exposure Enhancement
Ping Ni, Gvzelnur Imin, Rongren Xu, Zijian Wang, Yazhou Zhao · 2023
Aiming at the problems of low brightness and information distortion in most image dehazing algorithms, an image dehazing algorithm based on morphological and exposure enhancement was proposed. An initial transmittance is constructed based on dark channel prior, and through a linear model that can estimate haze density, then the transmittance is optimized by morphological closing and opening operations and gradient domain guided filtering. Atmospheric light is obtained by using minimum filter and quad-decomposition algorithm. An image compensation method is proposed to enhance the details of the dehazed image, an exposure enhancement method is used to improve the brightness, and finally converted to the YUV color space and the Y channel is denoised using the BM3D algorithm.