Title :
Adaptive Defogging of a Single Image
Author :
Yao, Bo ; Huang, Lei ; Liu, Changping
Author_Institution :
China Inst. of Autom., Chinese Acad. of Sci., Beijing, China
Abstract :
Based on the physical model of fogged images, a new method is proposed to enhance the visibility of a single image adaptively. In order to restrain the edge halation produced by virtual air light defogging method, the concept of neighboring pixel´s relative depth information is brought up. Input images may have different extent of disturbance of fog or haze, and they need different strength of defogging adaptively. Hence, we propose a method to calculate the deserved defogging ratio with valid edge intensity. Experimental results have proven the validity and robustness of our proposal.
Keywords :
image enhancement; adaptive image defogging; deserved defogging ratio; edge halation; neighboring pixel relative depth information; valid edge intensity; virtual air light defogging; visibility enhancement; Attenuation; Color; Computational intelligence; Design automation; Image restoration; Optical reflection; Pollution; Proposals; Rain; Robustness; defogging; defogging ratio; valid edge intensity;
Conference_Titel :
Computational Intelligence and Design, 2009. ISCID '09. Second International Symposium on
Conference_Location :
Changsha
Print_ISBN :
978-0-7695-3865-5
DOI :
10.1109/ISCID.2009.21