SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios
Detecting underwater objects is a complex task due to the inherent challenges of low contrast and intricate backgrounds. The wide range of object scales further complicates detection accuracy. To address these issues, we propose a Semantic Enhancement and Amplification Network (SEANet), a framework...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/10/3078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849326843582218240 |
|---|---|
| author | Ke Yang Xiao Wang Wei Wang Xin Yuan Xin Xu |
| author_facet | Ke Yang Xiao Wang Wei Wang Xin Yuan Xin Xu |
| author_sort | Ke Yang |
| collection | DOAJ |
| description | Detecting underwater objects is a complex task due to the inherent challenges of low contrast and intricate backgrounds. The wide range of object scales further complicates detection accuracy. To address these issues, we propose a Semantic Enhancement and Amplification Network (SEANet), a framework designed to enhance underwater object detection in complex visual scenarios. SEANet integrates three core components: the Multi-Scale Detail Amplification Module (MDAM), the Semantic Enhancement Feature Pyramid (SE-FPN), and the Contrast Enhancement Module (CEM). MDAM expands the receptive field across multiple scales, enabling the capture of subtle features that are often masked by background similarities. SE-FPN combines multi-scale features, optimizing feature representation and improving the synthesis of information across layers. CEM incorporates Fore-Background Contrast Attention (FBC) to amplify the contrast between foreground and background objects, thereby improving focus on low-contrast features. These components collectively enhance the network’s ability to effectively identify critical underwater features. Extensive experiments on three distinct underwater object detection datasets demonstrate the efficacy and robustness of SEANet. Specifically, the framework achieves the highest <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> (Average Precision) of 67.0% on the RUOD dataset, 53.0% on the URPC2021 dataset, and 71.5% on the DUO dataset. |
| format | Article |
| id | doaj-art-89d0c3e9b88f41cf8331fe5efe91d95f |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-89d0c3e9b88f41cf8331fe5efe91d95f2025-08-20T03:48:02ZengMDPI AGSensors1424-82202025-05-012510307810.3390/s25103078SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual ScenariosKe Yang0Xiao Wang1Wei Wang2Xin Yuan3Xin Xu4School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430081, ChinaHubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430081, ChinaHubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430081, ChinaHubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430081, ChinaHubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430081, ChinaDetecting underwater objects is a complex task due to the inherent challenges of low contrast and intricate backgrounds. The wide range of object scales further complicates detection accuracy. To address these issues, we propose a Semantic Enhancement and Amplification Network (SEANet), a framework designed to enhance underwater object detection in complex visual scenarios. SEANet integrates three core components: the Multi-Scale Detail Amplification Module (MDAM), the Semantic Enhancement Feature Pyramid (SE-FPN), and the Contrast Enhancement Module (CEM). MDAM expands the receptive field across multiple scales, enabling the capture of subtle features that are often masked by background similarities. SE-FPN combines multi-scale features, optimizing feature representation and improving the synthesis of information across layers. CEM incorporates Fore-Background Contrast Attention (FBC) to amplify the contrast between foreground and background objects, thereby improving focus on low-contrast features. These components collectively enhance the network’s ability to effectively identify critical underwater features. Extensive experiments on three distinct underwater object detection datasets demonstrate the efficacy and robustness of SEANet. Specifically, the framework achieves the highest <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> (Average Precision) of 67.0% on the RUOD dataset, 53.0% on the URPC2021 dataset, and 71.5% on the DUO dataset.https://www.mdpi.com/1424-8220/25/10/3078underwater object detectionlow contrastfeature pyramid networksemantic enhancement |
| spellingShingle | Ke Yang Xiao Wang Wei Wang Xin Yuan Xin Xu SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios Sensors underwater object detection low contrast feature pyramid network semantic enhancement |
| title | SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios |
| title_full | SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios |
| title_fullStr | SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios |
| title_full_unstemmed | SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios |
| title_short | SEANet: Semantic Enhancement and Amplification for Underwater Object Detection in Complex Visual Scenarios |
| title_sort | seanet semantic enhancement and amplification for underwater object detection in complex visual scenarios |
| topic | underwater object detection low contrast feature pyramid network semantic enhancement |
| url | https://www.mdpi.com/1424-8220/25/10/3078 |
| work_keys_str_mv | AT keyang seanetsemanticenhancementandamplificationforunderwaterobjectdetectionincomplexvisualscenarios AT xiaowang seanetsemanticenhancementandamplificationforunderwaterobjectdetectionincomplexvisualscenarios AT weiwang seanetsemanticenhancementandamplificationforunderwaterobjectdetectionincomplexvisualscenarios AT xinyuan seanetsemanticenhancementandamplificationforunderwaterobjectdetectionincomplexvisualscenarios AT xinxu seanetsemanticenhancementandamplificationforunderwaterobjectdetectionincomplexvisualscenarios |