Title :
A definition improving method for low visibility images
Author :
Li Deng ; Renhua Ge ; Ouxun Li
Author_Institution :
Department of Electronic Engineering, Guilin University of Aerospace Technology, China
Abstract :
Aiming at improving the quality and identification of vehicle video images in different kinds of low visibility weather, a novel definition enhancement method is proposed. The RGB debased image is converted to HSV color model first, of which the value component is successively processed by histogram equalization and definition improving method based on dark channel prior, finally combined with the other components of hue and saturation as the output image. Experiment results show that the presented method can significantly enhance the contrast and the identifiable degree of different kinds of images with low visibility.
Keywords :
HSV color model; dark channel prior; histogram equalization; low visibility;
Conference_Titel :
ICT and Energy Efficiency and Workshop on Information Theory and Security (CIICT 2012), Symposium on
Conference_Location :
Dublin
Electronic_ISBN :
978-1-84919-547-8
DOI :
10.1049/cp.2012.1879