Title: Contrast enhancement of fog and haze stereo images based on mobile computing

Authors: Yimin Qiu; Shihong Chen; Zhihua Cui

Addresses: Computer School of Wuhan University, Wuhan, China; School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan, China ' Computer School of Wuhan University, Wuhan, China; National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, China ' Department of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China

Abstract: The outdoor stereo vision systems which can be used to observe objects from multiple directions are affected by fog and haze thus causing a serious decline in visibility. Therefore, using image enhancement approaches in fog and haze stereoscopic systems can alleviate blurred images, help grasp the situation of road traffic from a three-dimensional point of view and improve visibility. In order to solve the limitations of stereoscopic simulation and traffic safety caused by the weather, we propose a novel contrast enhancement method of fog and haze stereoscopic images based on mobile computing to improve image quality in this paper. The proposed approach decomposes the original image of left and right views into wavelet domain, highlights the low-frequency coefficients by edge sharpening, and enhances it by modifications of high-frequency coefficients. Experimental results show that the proposed approach outperforms conventional approaches, provides more pleasant viewing and alleviates fog and haze phenomena.

Keywords: mobile computing; stereoscopic images; contrast enhancement; wavelet coefficient; human visual system; fog; haze; stereo vision; visibility; image enhancement; blurred images; road traffic; traffic safety; image quality; edge sharpening; simulation.

DOI: 10.1504/IJWMC.2014.059727

International Journal of Wireless and Mobile Computing, 2014 Vol.7 No.2, pp.137 - 146

Received: 07 Jan 2014
Accepted: 25 Jan 2014
Published online: 31 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article