Outdoor image restoration based on belief propagation algorithm and formalized MTF

Abstract

Single image dehazing technology can be applied to many fields. In order to solve this problem, an improved framework is proposed here, which can be used to estimate the light transmittance t in a given single input image and then the belief propagation (PB) algorithm is applied to image dehazing. At first, a coarse transmission map is calculated through Dark Channel Prior (DCP) knowledge. Next, the belief propagation methodology is introduced to correct the transmission map when the object in degraded image is similar to the airlight over a large local region. As a result, the transmission map can be estimated better and the important drawback of artifacts phenomenon can be avoid to some extent. At last, through this effective estimation to transmittance, the formalized MTF can be predicted to restore degraded images, then the haze-free scene contrasts can be better recovered. The experimental analysis results show that compared with defogged images acquired through DCP algorithms, our proposed algorithm can provide good results. Our method is more effective and robust.