Open AccessUnmanned aerial vehicle (UAV) image haze removal using dark channel prior
Author(s) -
Jun Yu,
Yaoheng Wang,
Shangbo Zhou,
Rumeng Zhai,
Saiao Huang
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1324/1/012036
Subject(s) - haze , computer science , channel (broadcasting) , artificial intelligence , computer vision , fidelity , aerial image , regularization (linguistics) , image (mathematics) , remote sensing , tree (set theory) , image restoration , image processing , geology , geography , mathematics , meteorology , computer network , telecommunications , mathematical analysis
The unmanned aerial vehicle (UAV) image taken in foggy or haze weather usually has lower contrast and fidelity, the quality of the image is seriously degraded. In this paper, we propose a dehazing model based on dark channel prior to dehaze the UAV image. We use a quad-tree hierarchical searching method to estimate the atmospheric light value, it can effectively avoid the influence of white objects in the image on the estimation of atmospheric light values. In the process of refining the medium transmission map, we propose a new regularization optimization scheme. Experimental results show that the proposed approach effectively recover the clear UAV image.