Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments
The marine environment is facing multiple challenges, and the development of underwater small target detection technology is crucial for protecting marine ecology. This paper focuses on the problem of small target detection in complex underwater environments and proposes an improved model based on t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/03/e3sconf_isgst2024_04014.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832098536398782464 |
|---|---|
| author | Xie Haozheng Xin Guanghong Kang Shuo Xie Qiongdan |
| author_facet | Xie Haozheng Xin Guanghong Kang Shuo Xie Qiongdan |
| author_sort | Xie Haozheng |
| collection | DOAJ |
| description | The marine environment is facing multiple challenges, and the development of underwater small target detection technology is crucial for protecting marine ecology. This paper focuses on the problem of small target detection in complex underwater environments and proposes an improved model based on the Deformable-DETR model. By introducing global response normalization and a fully convolutional mask autoencoder framework, the model’s feature aggregation ability and detection accuracy are enhanced. At the same time, a gradient harmonization mechanism is used to solve the problem of positive and negative sample imbalance, which enhances the model’s learning performance. Experimental results show that the improved model achieves a mAP value of 84.5% on the URPC2020 dataset, an increase of 1.7% over the original model. This technical optimization not only improves the accuracy of underwater small target detection but also contributes to marine ecological monitoring, rational utilization of resources, and environmental protection, promoting the realization of green environment and sustainable development goals. |
| format | Article |
| id | doaj-art-9e005f56624a40b99f7bc961e4e6f53c |
| institution | Kabale University |
| issn | 2267-1242 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj-art-9e005f56624a40b99f7bc961e4e6f53c2025-02-05T10:47:34ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016030401410.1051/e3sconf/202560304014e3sconf_isgst2024_04014Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environmentsXie Haozheng0Xin Guanghong1Kang Shuo2Xie Qiongdan3University of SanyaUniversity of SanyaUniversity of SanyaUniversity of SanyaThe marine environment is facing multiple challenges, and the development of underwater small target detection technology is crucial for protecting marine ecology. This paper focuses on the problem of small target detection in complex underwater environments and proposes an improved model based on the Deformable-DETR model. By introducing global response normalization and a fully convolutional mask autoencoder framework, the model’s feature aggregation ability and detection accuracy are enhanced. At the same time, a gradient harmonization mechanism is used to solve the problem of positive and negative sample imbalance, which enhances the model’s learning performance. Experimental results show that the improved model achieves a mAP value of 84.5% on the URPC2020 dataset, an increase of 1.7% over the original model. This technical optimization not only improves the accuracy of underwater small target detection but also contributes to marine ecological monitoring, rational utilization of resources, and environmental protection, promoting the realization of green environment and sustainable development goals.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/03/e3sconf_isgst2024_04014.pdf |
| spellingShingle | Xie Haozheng Xin Guanghong Kang Shuo Xie Qiongdan Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments E3S Web of Conferences |
| title | Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments |
| title_full | Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments |
| title_fullStr | Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments |
| title_full_unstemmed | Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments |
| title_short | Efficient-Deformable-DETR: Enhancing underwater small target detection in complex environments |
| title_sort | efficient deformable detr enhancing underwater small target detection in complex environments |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/03/e3sconf_isgst2024_04014.pdf |
| work_keys_str_mv | AT xiehaozheng efficientdeformabledetrenhancingunderwatersmalltargetdetectionincomplexenvironments AT xinguanghong efficientdeformabledetrenhancingunderwatersmalltargetdetectionincomplexenvironments AT kangshuo efficientdeformabledetrenhancingunderwatersmalltargetdetectionincomplexenvironments AT xieqiongdan efficientdeformabledetrenhancingunderwatersmalltargetdetectionincomplexenvironments |