Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending
In this paper, we propose a novel method to address the nighttime single image dehazing problem. Estimation of the ambient illumination map and transmission map are the key steps of modern dehazing approaches. For hazy scenes at night, ambient illumination is usually not globally isotropic as a nigh...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8805086/ |
| _version_ | 1818877677543620608 |
|---|---|
| author | Teng Yu Kang Song Pu Miao Guowei Yang Huan Yang Chenglizhao Chen |
| author_facet | Teng Yu Kang Song Pu Miao Guowei Yang Huan Yang Chenglizhao Chen |
| author_sort | Teng Yu |
| collection | DOAJ |
| description | In this paper, we propose a novel method to address the nighttime single image dehazing problem. Estimation of the ambient illumination map and transmission map are the key steps of modern dehazing approaches. For hazy scenes at night, ambient illumination is usually not globally isotropic as a nighttime scene typically contains multiple light sources. Frequently, Light source regions and non-light source regions exhibit distinct color features. However, existing nighttime dehazing methods have been attempting to process these two regions based on identical prior assumptions. Moreover, the commonly-used local maximum pixel method tends to over-estimate the ambient illumination. These two drawbacks result in color distortions and halo artifacts around the light source regions in the output images. In this work, we present a pixel-wise alpha blending method for estimating the transmission map, where the transmissions estimated from dark channel prior (non-light source region) and the proposed bright channel prior (light source region) are effectively blended into one transmission map guided by a brightness-aware weights map. Based on the Retinex theory, a channel difference guided filtering method is proposed to estimate the ambient illumination, which produces a spatially variant low-frequency passband that selectively retains the high-frequency edge details. Extensive experiments on the benchmarks demonstrate that our method outperforms the state-of-the-art methods for nighttime image dehazing, especially in terms of color consistency and halo artifacts reduction in the dehazed images. |
| first_indexed | 2024-12-19T14:02:05Z |
| format | Article |
| id | doaj.art-c0e679650665424ab75d142df6bdcce6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T14:02:05Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c0e679650665424ab75d142df6bdcce62022-12-21T20:18:26ZengIEEEIEEE Access2169-35362019-01-01711461911463010.1109/ACCESS.2019.29360498805086Nighttime Single Image Dehazing via Pixel-Wise Alpha BlendingTeng Yu0https://orcid.org/0000-0001-5703-9393Kang Song1Pu Miao2Guowei Yang3Huan Yang4https://orcid.org/0000-0001-5810-0248Chenglizhao Chen5https://orcid.org/0000-0001-9982-5667School of Electronic Information, Qingdao University, Qingdao, ChinaSchool of Electronic Information, Qingdao University, Qingdao, ChinaSchool of Electronic Information, Qingdao University, Qingdao, ChinaSchool of Electronic Information, Qingdao University, Qingdao, ChinaSchool of Computer Science and Technology, Qingdao University, Qingdao, ChinaSchool of Computer Science and Technology, Qingdao University, Qingdao, ChinaIn this paper, we propose a novel method to address the nighttime single image dehazing problem. Estimation of the ambient illumination map and transmission map are the key steps of modern dehazing approaches. For hazy scenes at night, ambient illumination is usually not globally isotropic as a nighttime scene typically contains multiple light sources. Frequently, Light source regions and non-light source regions exhibit distinct color features. However, existing nighttime dehazing methods have been attempting to process these two regions based on identical prior assumptions. Moreover, the commonly-used local maximum pixel method tends to over-estimate the ambient illumination. These two drawbacks result in color distortions and halo artifacts around the light source regions in the output images. In this work, we present a pixel-wise alpha blending method for estimating the transmission map, where the transmissions estimated from dark channel prior (non-light source region) and the proposed bright channel prior (light source region) are effectively blended into one transmission map guided by a brightness-aware weights map. Based on the Retinex theory, a channel difference guided filtering method is proposed to estimate the ambient illumination, which produces a spatially variant low-frequency passband that selectively retains the high-frequency edge details. Extensive experiments on the benchmarks demonstrate that our method outperforms the state-of-the-art methods for nighttime image dehazing, especially in terms of color consistency and halo artifacts reduction in the dehazed images.https://ieeexplore.ieee.org/document/8805086/Nighttime image dehazingimage restorationalpha blending |
| spellingShingle | Teng Yu Kang Song Pu Miao Guowei Yang Huan Yang Chenglizhao Chen Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending IEEE Access Nighttime image dehazing image restoration alpha blending |
| title | Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending |
| title_full | Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending |
| title_fullStr | Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending |
| title_full_unstemmed | Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending |
| title_short | Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending |
| title_sort | nighttime single image dehazing via pixel wise alpha blending |
| topic | Nighttime image dehazing image restoration alpha blending |
| url | https://ieeexplore.ieee.org/document/8805086/ |
| work_keys_str_mv | AT tengyu nighttimesingleimagedehazingviapixelwisealphablending AT kangsong nighttimesingleimagedehazingviapixelwisealphablending AT pumiao nighttimesingleimagedehazingviapixelwisealphablending AT guoweiyang nighttimesingleimagedehazingviapixelwisealphablending AT huanyang nighttimesingleimagedehazingviapixelwisealphablending AT chenglizhaochen nighttimesingleimagedehazingviapixelwisealphablending |