An improved dehazing algorithm of aerial high-definition image

Wentao Jiang; Ming Ji; Xiying Huang; Chao Wang; Yizhou Yang; Tao Li; Jiaoying Wang; Ying Zhang

doi:10.1117/12.2229845

26 January 2016 An improved dehazing algorithm of aerial high-definition image

Wentao Jiang, Ming Ji, Xiying Huang, Chao Wang, Yizhou Yang, Tao Li, Jiaoying Wang, Ying Zhang

Proceedings Volume 9796, Selected Papers of the Photoelectronic Technology Committee Conferences held November 2015; 97962T (2016) https://doi.org/10.1117/12.2229845
Event: Selected Proceedings of the Chinese Society for Optical Engineering Conferences held November 2015, 2015, Various, China

Abstract

For unmanned aerial vehicle(UAV) images, the sensor can not get high quality images due to fog and haze weather. To solve this problem, An improved dehazing algorithm of aerial high-definition image is proposed. Based on the model of dark channel prior, the new algorithm firstly extracts the edges from crude estimated transmission map and expands the extracted edges. Then according to the expended edges, the algorithm sets a threshold value to divide the crude estimated transmission map into different areas and makes different guided filter on the different areas compute the optimized transmission map. The experimental results demonstrate that the performance of the proposed algorithm is substantially the same as the one based on dark channel prior and guided filter. The average computation time of the new algorithm is around 40% of the one as well as the detection ability of UAV image is improved effectively in fog and haze weather.

Citation Download Citation

Wentao Jiang, Ming Ji, Xiying Huang, Chao Wang, Yizhou Yang, Tao Li, Jiaoying Wang, and Ying Zhang "An improved dehazing algorithm of aerial high-definition image", Proc. SPIE 9796, Selected Papers of the Photoelectronic Technology Committee Conferences held November 2015, 97962T (26 January 2016); https://doi.org/10.1117/12.2229845

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available