Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution
Underwater object detection (UOD) has attracted widespread attention, being of great significance for marine resource management, underwater security and defense, underwater infrastructure inspection, etc. However, high-quality UOD tasks often encounter challenges such as image quality degradation,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/9/1733 |
| _version_ | 1797579342690123776 |
|---|---|
| author | Xun Ji Guo-Peng Liu Cheng-Tao Cai |
| author_facet | Xun Ji Guo-Peng Liu Cheng-Tao Cai |
| author_sort | Xun Ji |
| collection | DOAJ |
| description | Underwater object detection (UOD) has attracted widespread attention, being of great significance for marine resource management, underwater security and defense, underwater infrastructure inspection, etc. However, high-quality UOD tasks often encounter challenges such as image quality degradation, complex backgrounds, and occlusions between objects at different scales. This paper presents a collaborative framework for UOD via joint image enhancement and super-resolution to address the above problems. Specifically, a joint-oriented framework is constructed incorporating underwater image enhancement and super-resolution techniques. The proposed framework is capable of generating a detection-favoring appearance to provide more visual cues for UOD tasks. Furthermore, a plug-and-play self-attention mechanism, termed multihead blurpooling fusion network (MBFNet), is developed to capture sufficient contextual information by focusing on the dependencies between multiscale feature maps, so that the UOD performance of our proposed framework can be further facilitated. A comparative study on the popular URPC2020 and Brackish datasets demonstrates the superior performance of our proposed collaborative framework, and the ablation study also validates the effectiveness of each component within the framework. |
| first_indexed | 2024-03-10T22:34:46Z |
| format | Article |
| id | doaj.art-00b1585aeab949e8a8a46bc8297b9978 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T22:34:46Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-00b1585aeab949e8a8a46bc8297b99782023-11-19T11:26:39ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-09-01119173310.3390/jmse11091733Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-ResolutionXun Ji0Guo-Peng Liu1Cheng-Tao Cai2College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaUnderwater object detection (UOD) has attracted widespread attention, being of great significance for marine resource management, underwater security and defense, underwater infrastructure inspection, etc. However, high-quality UOD tasks often encounter challenges such as image quality degradation, complex backgrounds, and occlusions between objects at different scales. This paper presents a collaborative framework for UOD via joint image enhancement and super-resolution to address the above problems. Specifically, a joint-oriented framework is constructed incorporating underwater image enhancement and super-resolution techniques. The proposed framework is capable of generating a detection-favoring appearance to provide more visual cues for UOD tasks. Furthermore, a plug-and-play self-attention mechanism, termed multihead blurpooling fusion network (MBFNet), is developed to capture sufficient contextual information by focusing on the dependencies between multiscale feature maps, so that the UOD performance of our proposed framework can be further facilitated. A comparative study on the popular URPC2020 and Brackish datasets demonstrates the superior performance of our proposed collaborative framework, and the ablation study also validates the effectiveness of each component within the framework.https://www.mdpi.com/2077-1312/11/9/1733underwater object detectionunderwater image enhancementsuper-resolutionjoint learningdeep learning |
| spellingShingle | Xun Ji Guo-Peng Liu Cheng-Tao Cai Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution Journal of Marine Science and Engineering underwater object detection underwater image enhancement super-resolution joint learning deep learning |
| title | Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution |
| title_full | Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution |
| title_fullStr | Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution |
| title_full_unstemmed | Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution |
| title_short | Collaborative Framework for Underwater Object Detection via Joint Image Enhancement and Super-Resolution |
| title_sort | collaborative framework for underwater object detection via joint image enhancement and super resolution |
| topic | underwater object detection underwater image enhancement super-resolution joint learning deep learning |
| url | https://www.mdpi.com/2077-1312/11/9/1733 |
| work_keys_str_mv | AT xunji collaborativeframeworkforunderwaterobjectdetectionviajointimageenhancementandsuperresolution AT guopengliu collaborativeframeworkforunderwaterobjectdetectionviajointimageenhancementandsuperresolution AT chengtaocai collaborativeframeworkforunderwaterobjectdetectionviajointimageenhancementandsuperresolution |