BELUGA WHALE DETECTION FROM SATELLITE IMAGERY WITH POINT LABELS
文献类型：期刊论文
| 作者 | Zheng, Yijie4,6; Yang, Jinxuan2,3; Chen, Yu1,3; Wang, Yaxuan5,7; Lu, Yihang4,6; Li, Guoying6 |
| 刊名 | IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
 |
| 出版日期 | 2025 |
| 卷号 | N/A页码:1298-1302 |
| 关键词 | beluga whale satellite imagery promptable segmentation object detection |
| ISSN号 | 2153-6996 |
| DOI | 10.1109/IGARSS55030.2025.11243110 |
| 产权排序 | 4 |
| 文献子类 | Proceedings Paper |
| 英文摘要 | Very high-resolution (VHR) satellite imagery has emerged as a powerful tool for monitoring marine animals on a large scale. However, existing deep learning-based whale detection methods usually require manually created, high-quality bounding box annotations, which are labor-intensive to produce. Moreover, existing studies often exclude uncertain whales, individuals that have ambiguous appearances in satellite imagery, limiting the applicability of these models in real-world scenarios. To address these limitations, this study introduces an automated pipeline for detecting beluga whales and harp seals in VHR satellite imagery. The pipeline leverages point annotations and the Segment Anything Model (SAM) to generate precise bounding box annotations, which are used to train YOLOv8 for multiclass detection of certain whales, uncertain whales, and harp seals. Experimental results demonstrated that SAMgenerated annotations significantly improved detection performance, achieving higher F1-scores compared to traditional bufferbased annotations. YOLOv8 trained on SAM-labeled boxes achieved an overall F1-score of 72.2% for whales overall and 70.3% for harp seals, with superior performance in dense scenes. The proposed approach not only reduces the manual effort required for annotation but also enhances the detection of uncertain whales, offering a more comprehensive solution for marine animal monitoring. This method holds great potential for extending to other species, habitats, and remote sensing platforms, as well as for estimating whale biometrics, thereby advancing ecological monitoring and conservation efforts. The codes for our label and detection pipeline are publicly available at http://github.com/voyagerxvoyagerx/beluga-seeker. |
| URL标识 | 查看原文 |
| WOS研究方向 | Physical Geography ; Geology ; Instruments & Instrumentation ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001697407700272 |
| 出版者 | IEEE |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221253]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Li, Guoying |
| 作者单位 | 1.Chinese Res Inst Environm Sci, Beijing, Peoples R China; 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China; 3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China; 4.Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing, Peoples R China; 5.Chinese Acad Sci, Tech Inst Phys & Chem, Beijing, Peoples R China 6.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China; 7.Univ Chinese Acad Sci, Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zheng, Yijie,Yang, Jinxuan,Chen, Yu,et al. BELUGA WHALE DETECTION FROM SATELLITE IMAGERY WITH POINT LABELS[J]. IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM,2025,N/A:1298-1302. |
| APA | Zheng, Yijie,Yang, Jinxuan,Chen, Yu,Wang, Yaxuan,Lu, Yihang,&Li, Guoying.(2025).BELUGA WHALE DETECTION FROM SATELLITE IMAGERY WITH POINT LABELS.IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM,N/A,1298-1302. |
| MLA | Zheng, Yijie,et al."BELUGA WHALE DETECTION FROM SATELLITE IMAGERY WITH POINT LABELS".IGARSS 2025-2025 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM N/A(2025):1298-1302. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。