Two-click based fast small object annotation in remote sensing images.

Lei, Lu; Fang, Zhenyu; Ren, Jinchang; Gamba, Paolo; Zheng, Jiangbin; Zhao, Huimin

Abstract

In the remote sensing field, detecting small objects is a pivotal task, yet achieving high performance in deep learning-based detectors heavily relies on extensive data annotation. The challenge intensifies as small objects in remote sensing imagery are typically densely distributed and numerous, leading to a substantial increase in the cost of creating large-scale annotated datasets. This elevated cost poses significant limitations on the application and advancement of small object detection. To address this issue, a Point-Based Annotation method (PBA) is proposed, which generates bounding boxes through graph-based segmentation. In this framework, user annotations categorize nodes into three distinct classes - positive, negative, and to-cut-facilitating a more intuitive and efficient annotation process. Utilizing the max-flow algorithm, our method seamlessly generates Oriented Bounding Boxes (OBBOX) from these classified nodes. The efficacy of PBA is underscored by our empirical findings. Notably, annotation efficiency is enhanced by at least 40%, a significant leap forward. Moreover, the Intersection over Union (IoU) metric of our OBBOX outperforms existing methods like "Segment Anything Model" by 10%. Finally, when applied in training, models annotated with PBA exhibit a 3% increase in the mean Average Precision (mAP) compared to those using traditional annotation methods. These results not only affirm the technical superiority of PBA but also its practical impact in advancing small object detection in remote sensing.

Citation

LEI, L., FANG, Z., REN, J., GAMBA, P., ZHENG, J. and ZHAO, H. 2024. Two-click based fast small object annotation in remote sensing images. IEEE transactions of geoscience and remote sensing [online], 62, article number 5639513. Available from: https://doi.org/10.1109/tgrs.2024.3442732

• Journal Article Type: Article
• Acceptance Date: Aug 13, 2024
• Online Publication Date: Aug 13, 2024
• Publication Date: Dec 31, 2024
• Deposit Date: Aug 16, 2024
• Publicly Available Date: Aug 16, 2024
• Journal: IEEE transactions on geoscience and remote sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 62
• Article Number: 5639513
• DOI: https://doi.org/10.1109/TGRS.2024.3442732
• Keywords: Remote sensing; Small object detection; Data annotation; Deep learning; Cost-efficiency in data processing
• Public URL: https://rgu-repository.worktribe.com/output/2434429