Proceedings of the Korean Society of Broadcast Engineers Conference (한국방송∙미디어공학회:학술대회논문집)
- 2018.06a
- /
- Pages.116-119
- /
- 2018
A fast single image dehazing method based on statistical analysis
- Bui, Minh Trung (Kyung Hee University) ;
- Bang, Seongbae (Kyung Hee University) ;
-
Kim, Wonha
(Kyung Hee University)
- Published : 2018.06.20
Abstract
In this paper, we propose a new single-image dehazing method. The proposed method constructs color ellipsoids that are statistically fitted to haze pixel clusters in RGB space and then calculates the transmission values through color ellipsoid geometry. The transmission values generated by the proposed method maximize the contrast of dehazed pixels, while preventing over-saturated pixels. The values are also statistically robust because they are calculated from the averages of the haze pixel values. Furthermore, rather than apply a highly complex refinement process to reduce halo or unnatural artifacts, we embed a fuzzy segmentation process into the construction of the color ellipsoid so that the proposed method simultaneously executes the transmission calculation and the refinement process. The results of an experimental performance evaluation verify that compared to prevailing dehazing methods the proposed method performs effectively across a wide range of haze and noise levels without causing any visible artifacts. Moreover, the relatively low complexity of the proposed method will facilitate its real-time applications.
Keywords