期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 22, 期 1, 页码 30-44出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2019.2922127
关键词
l(0)-norm; gradient; dehazing; edge-preserving filtering; optimization; guided filtering
资金
- Institute for Information & Communications Technology Promotion grant - Korea government (MSIT) [2017-0-00250]
- Intelligent Defense Boundary Surveillance Technology Using Collaborative Reinforced Learning of Embedded Edge Camera and Image Analysis
- National Research Foundation of Korea - Korea government (MSIP) [NRF-2014R1A2A1A11049986]
Outdoor images are subject to degradation regarding contrast and color because atmospheric particles scatter incoming light to a camera. Existing haze models that employ model-based dehazing methods cannot avoid the dehazing artifacts. These artifacts include color distortion and overenhancement around object boundaries because of the incorrect transmission estimation from a depth error in the skyline and the wrong haze information, especially in bright objects. To overcome this problem, we present a novel optimization-based dehazing algorithm that combines radiance and reflectance components with an additional refinement using a structure-guided $\ell _0$-norm filter. More specifically, we first estimate a weak reflectance map and optimize the transmission map based on the estimated reflectance map. Next, we estimate the structure-guided $\ell _0$ transmission map to remove the dehazing artifacts. The experimental results show that the proposed method outperforms state-of-the-art algorithms in terms of qualitative and quantitative measures compared with simulated image pairs. In addition, the real-world enhancement results demonstrate that the proposed method can provide a high-quality image without undesired artifacts. Furthermore, the guided $\ell _0$-norm filter can remove textures while preserving edges for general image enhancement algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据