UDA‐Net: Densely attention network for underwater image enhancement
Abstract Underwater imaging usually suffers from negative impacts due to the absorption and scattering effects in water. Underwater images thus have unfavourable visual quality to support the work in such environment. This paper addresses the problem of image improvement for single underwater image....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-02-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12061 |
| _version_ | 1798027594059218944 |
|---|---|
| author | Yang Li Rong Chen |
| author_facet | Yang Li Rong Chen |
| author_sort | Yang Li |
| collection | DOAJ |
| description | Abstract Underwater imaging usually suffers from negative impacts due to the absorption and scattering effects in water. Underwater images thus have unfavourable visual quality to support the work in such environment. This paper addresses the problem of image improvement for single underwater image. The core idea lies in a new enhancement model based on deep learning architecture, in which a feature‐level attention model is developed. This model is a multi‐scale grid convolutional neural network that can facilitate fusing different types of information during representation learning. According to this information combination, a synergistic pooling mechanism is proposed to extract the channel‐wise attention maps to derive the locally weighted features. Therefore, this model can adaptively focus on the feature regions corresponding to degraded patches in one underwater image and improve these patches consistently. Comprehensive experiments are conducted on benchmark and natural underwater images, and it can be demonstrated that this model is effective. |
| first_indexed | 2024-04-11T18:54:00Z |
| format | Article |
| id | doaj.art-53f43fd84f1e485e81bdb11a49333925 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-11T18:54:00Z |
| publishDate | 2021-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-53f43fd84f1e485e81bdb11a493339252022-12-22T04:08:14ZengWileyIET Image Processing1751-96591751-96672021-02-0115377478510.1049/ipr2.12061UDA‐Net: Densely attention network for underwater image enhancementYang Li0Rong Chen1College of Information Science and Technology Dalian Maritime University Dalian ChinaCollege of Information Science and Technology Dalian Maritime University Dalian ChinaAbstract Underwater imaging usually suffers from negative impacts due to the absorption and scattering effects in water. Underwater images thus have unfavourable visual quality to support the work in such environment. This paper addresses the problem of image improvement for single underwater image. The core idea lies in a new enhancement model based on deep learning architecture, in which a feature‐level attention model is developed. This model is a multi‐scale grid convolutional neural network that can facilitate fusing different types of information during representation learning. According to this information combination, a synergistic pooling mechanism is proposed to extract the channel‐wise attention maps to derive the locally weighted features. Therefore, this model can adaptively focus on the feature regions corresponding to degraded patches in one underwater image and improve these patches consistently. Comprehensive experiments are conducted on benchmark and natural underwater images, and it can be demonstrated that this model is effective.https://doi.org/10.1049/ipr2.12061Optical, image and video signal processingComputer vision and image processing techniquesNeural nets |
| spellingShingle | Yang Li Rong Chen UDA‐Net: Densely attention network for underwater image enhancement IET Image Processing Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| title | UDA‐Net: Densely attention network for underwater image enhancement |
| title_full | UDA‐Net: Densely attention network for underwater image enhancement |
| title_fullStr | UDA‐Net: Densely attention network for underwater image enhancement |
| title_full_unstemmed | UDA‐Net: Densely attention network for underwater image enhancement |
| title_short | UDA‐Net: Densely attention network for underwater image enhancement |
| title_sort | uda net densely attention network for underwater image enhancement |
| topic | Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| url | https://doi.org/10.1049/ipr2.12061 |
| work_keys_str_mv | AT yangli udanetdenselyattentionnetworkforunderwaterimageenhancement AT rongchen udanetdenselyattentionnetworkforunderwaterimageenhancement |