Real-Time Dehazing via Multiscale Products for Vision Control

Abstract

In this study, a dehazing algorithm based on multiscale product (MSP) prior is presented. In this method, first, the observed hazy image is decomposed into its approximation and detail subbands by undecimated Laplacian decomposition. Then the MSPs of the approximation subbands for each band of the image is calculated to obtain the MSP prior. This prior keeps the significant information of the image, whereas it is capable of detecting the haze in the image. By the use of this prior and the hazy image model, a fast and robust dehazing algorithm is obtained. The proposed method is compared with commonly used methods. The results demonstrate that the proposed algorithm is better than the former methods. Being a fast and robust algorithm, the proposed method has also been applied to a real time robotic vision control system. © 2017 IEEE.