文献类型：期刊文献

英文题名：Single image dehazing with a physical model and dark channel prior

作者：Jin-Bao Wang[1]; Ning He[1]; Lu-Lu Zhang[1]; Ke Lu[2]

第一作者：Jin-Bao Wang

机构：[1] Beijing Key Lab. of Inf. Service Eng., Beijing Union Univ., Beijing, China; [2] Chinese Acad. of Sci., Beijing, China

第一机构：北京联合大学

年份：0

卷号：149

起止页码：718-28

外文期刊名：Neurocomputing

收录：EI(收录号：14742426)

语种：英文

外文关键词：gradient methods - image colour analysis - image restoration

摘要：We propose a single image dehazing method that is based on a physical model and the dark channel prior principle. The selection of an atmospheric light value is directly responsible for the color authenticity and contrast of the resulting image. Our choice of atmospheric light is based on a variogram, which slowly weakens areas in the image that do not conform to the dark channel prior. Additionally, we propose a fast transmission estimation algorithm to shorten the processing time. Along with a subjective evaluation, the image quality was also evaluated using three indicators: MSE, PSNR, and average gradient. Our experimental results show that the proposed method can obtain accurate dehazing results and improve the operational efficiency. [All rights reserved Elsevier].