A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models f...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2471 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733768539013120 |
|---|---|
| author | Zhuhua Hu Wei Wu Ziqi Yang Yaochi Zhao Lewei Xu Lingkai Kong Yunpei Chen Lihang Chen Gaosheng Liu |
| author_facet | Zhuhua Hu Wei Wu Ziqi Yang Yaochi Zhao Lewei Xu Lingkai Kong Yunpei Chen Lihang Chen Gaosheng Liu |
| author_sort | Zhuhua Hu |
| collection | DOAJ |
| description | Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and <inline-formula><math display="inline"><semantics><msub><mi>AP</mi><mn>50</mn></msub></semantics></math></inline-formula> scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications. |
| format | Article |
| id | doaj-art-4480a5d853a64161bb7f0ac3bacee145 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-4480a5d853a64161bb7f0ac3bacee1452025-08-20T03:07:58ZengMDPI AGRemote Sensing2072-42922025-07-011714247110.3390/rs17142471A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing ImageryZhuhua Hu0Wei Wu1Ziqi Yang2Yaochi Zhao3Lewei Xu4Lingkai Kong5Yunpei Chen6Lihang Chen7Gaosheng Liu8School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Cyberspace Security, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaVessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and <inline-formula><math display="inline"><semantics><msub><mi>AP</mi><mn>50</mn></msub></semantics></math></inline-formula> scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications.https://www.mdpi.com/2072-4292/17/14/2471object detectionYOLOsmall objectsclass imbalancecost-sensitive |
| spellingShingle | Zhuhua Hu Wei Wu Ziqi Yang Yaochi Zhao Lewei Xu Lingkai Kong Yunpei Chen Lihang Chen Gaosheng Liu A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery Remote Sensing object detection YOLO small objects class imbalance cost-sensitive |
| title | A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery |
| title_full | A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery |
| title_fullStr | A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery |
| title_full_unstemmed | A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery |
| title_short | A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery |
| title_sort | cost sensitive small vessel detection method for maritime remote sensing imagery |
| topic | object detection YOLO small objects class imbalance cost-sensitive |
| url | https://www.mdpi.com/2072-4292/17/14/2471 |
| work_keys_str_mv | AT zhuhuahu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT weiwu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT ziqiyang acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT yaochizhao acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT leweixu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT lingkaikong acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT yunpeichen acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT lihangchen acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT gaoshengliu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT zhuhuahu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT weiwu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT ziqiyang costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT yaochizhao costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT leweixu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT lingkaikong costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT yunpeichen costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT lihangchen costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery AT gaoshengliu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery |