A High-Performance and Lightweight Maritime Target Detection Algorithm
Maritime surveillance video (MSV) target detection systems are important for maritime security and ocean economy. Hindered by many complex factors, the existing MSV target detection systems have low detection accuracy. These factors include target distance, potential occlusion from rain and fog, and...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/6/1012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849340488514011136 |
|---|---|
| author | Shidan Sun Zhiping Xu Xiaochun Cao Jiachun Zheng Jiawen Yang Ni Jin |
| author_facet | Shidan Sun Zhiping Xu Xiaochun Cao Jiachun Zheng Jiawen Yang Ni Jin |
| author_sort | Shidan Sun |
| collection | DOAJ |
| description | Maritime surveillance video (MSV) target detection systems are important for maritime security and ocean economy. Hindered by many complex factors, the existing MSV target detection systems have low detection accuracy. These factors include target distance, potential occlusion from rain and fog, and limited computing power of edge devices. To overcome these factors, a high performance and lightweight maritime target detection algorithm (HPMTD) is proposed in this paper. HPMTD consists of three modules: feature extraction, shallow feature progressive fusion (SFPF), and multi-scale sensing head. In the feature extraction module, a global coordinate attention-optimized offset regression module is proposed for deformable convolution. Thus, the ability to handle low visibility and target occlusion issues is enhanced. In the SFPF module, the ghost dynamic convolution combined with low-cost adaptive spatial feature fusion is proposed. In this way, lightweight design can be realized, and multi-scale target-detecting capacity can be increased. Furthermore, multi-scale sensing head is incorporated to learn and fuse scale features more effectively, thus improving localization accuracy. To evaluate the performance of the proposed algorithm, the Singapore Maritime Dataset is adopted in our experiments. The experimental results show that the proposed algorithm can achieve a nearly 10 percent mean average precision value improvement with nearly half the model size, compared with counterparts. Furthermore, the proposed algorithm runs three times faster with only half of the computation resources, and maintains nearly same accuracy in the maritime surface with low visibility. These results demonstrate that the HPMTD achieves lightweight and high-precision detection of marine targets. |
| format | Article |
| id | doaj-art-a84ffc0215d14c2dbc2b90ba77b0da82 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-a84ffc0215d14c2dbc2b90ba77b0da822025-08-20T03:43:54ZengMDPI AGRemote Sensing2072-42922025-03-01176101210.3390/rs17061012A High-Performance and Lightweight Maritime Target Detection AlgorithmShidan Sun0Zhiping Xu1Xiaochun Cao2Jiachun Zheng3Jiawen Yang4Ni Jin5School of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaMaritime surveillance video (MSV) target detection systems are important for maritime security and ocean economy. Hindered by many complex factors, the existing MSV target detection systems have low detection accuracy. These factors include target distance, potential occlusion from rain and fog, and limited computing power of edge devices. To overcome these factors, a high performance and lightweight maritime target detection algorithm (HPMTD) is proposed in this paper. HPMTD consists of three modules: feature extraction, shallow feature progressive fusion (SFPF), and multi-scale sensing head. In the feature extraction module, a global coordinate attention-optimized offset regression module is proposed for deformable convolution. Thus, the ability to handle low visibility and target occlusion issues is enhanced. In the SFPF module, the ghost dynamic convolution combined with low-cost adaptive spatial feature fusion is proposed. In this way, lightweight design can be realized, and multi-scale target-detecting capacity can be increased. Furthermore, multi-scale sensing head is incorporated to learn and fuse scale features more effectively, thus improving localization accuracy. To evaluate the performance of the proposed algorithm, the Singapore Maritime Dataset is adopted in our experiments. The experimental results show that the proposed algorithm can achieve a nearly 10 percent mean average precision value improvement with nearly half the model size, compared with counterparts. Furthermore, the proposed algorithm runs three times faster with only half of the computation resources, and maintains nearly same accuracy in the maritime surface with low visibility. These results demonstrate that the HPMTD achieves lightweight and high-precision detection of marine targets.https://www.mdpi.com/2072-4292/17/6/1012maritime target detectiondeformable convolutionmulti-scale feature fusionconvolutional neural network |
| spellingShingle | Shidan Sun Zhiping Xu Xiaochun Cao Jiachun Zheng Jiawen Yang Ni Jin A High-Performance and Lightweight Maritime Target Detection Algorithm Remote Sensing maritime target detection deformable convolution multi-scale feature fusion convolutional neural network |
| title | A High-Performance and Lightweight Maritime Target Detection Algorithm |
| title_full | A High-Performance and Lightweight Maritime Target Detection Algorithm |
| title_fullStr | A High-Performance and Lightweight Maritime Target Detection Algorithm |
| title_full_unstemmed | A High-Performance and Lightweight Maritime Target Detection Algorithm |
| title_short | A High-Performance and Lightweight Maritime Target Detection Algorithm |
| title_sort | high performance and lightweight maritime target detection algorithm |
| topic | maritime target detection deformable convolution multi-scale feature fusion convolutional neural network |
| url | https://www.mdpi.com/2072-4292/17/6/1012 |
| work_keys_str_mv | AT shidansun ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT zhipingxu ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT xiaochuncao ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT jiachunzheng ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT jiawenyang ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT nijin ahighperformanceandlightweightmaritimetargetdetectionalgorithm AT shidansun highperformanceandlightweightmaritimetargetdetectionalgorithm AT zhipingxu highperformanceandlightweightmaritimetargetdetectionalgorithm AT xiaochuncao highperformanceandlightweightmaritimetargetdetectionalgorithm AT jiachunzheng highperformanceandlightweightmaritimetargetdetectionalgorithm AT jiawenyang highperformanceandlightweightmaritimetargetdetectionalgorithm AT nijin highperformanceandlightweightmaritimetargetdetectionalgorithm |