用异常检测+人工标注，高效发现卫星图像中的鲸鱼。
Where are the Whales: A Human-in-the-loop Detection Method for Identifying Whales in High-resolution Satellite Imagery
- 通过统计异常点检测，自动标记可能有鲸鱼的区域。
- 在三组测试中召回率达90.3%~96.4%，专家检查范围缩小至不足2平方公里。
- 无需标注数据，适合大规模海洋哺乳动物监测应用。
有效监测鲸鱼种群对保护至关重要，但传统调查方法成本高且难扩展。尽管先前研究已证明可在极高清（VHR）卫星影像中识别鲸鱼，但大规模自动化检测仍面临标注数据缺乏、图像质量与环境差异大、构建稳健机器学习管道成本高等挑战。本文提出一种半自动化方法：利用统计异常检测识别空间异常点（即“有趣点”），再通过网页标注界面供专家快速确认。在三组含已知鲸鱼标注的基准场景中评估，召回率达90.3%至96.4%，专家需检查区域面积最多减少99.8%——从超1,000平方公里降至不足2平方公里。该方法不依赖标注训练数据，为未来基于卫星的海洋哺乳动物监测提供了可扩展的第一步。代码已开源至https://github.com/microsoft/whales。
原文摘要 · Abstract (English)
Effective monitoring of whale populations is critical for conservation, but traditional survey methods are expensive and difficult to scale. While prior work has shown that whales can be identified in very high-resolution (VHR) satellite imagery, large-scale automated detection remains challenging due to a lack of annotated imagery, variability in image quality and environmental conditions, and the cost of building robust machine learning pipelines over massive remote sensing archives. We present a semi-automated approach for surfacing possible whale detections in VHR imagery using a statistical anomaly detection method that flags spatial outliers, i.e. "interesting points". We pair this detector with a web-based labeling interface designed to enable experts to quickly annotate the interesting points. We evaluate our system on three benchmark scenes with known whale annotations and achieve recalls of 90.3% to 96.4%, while reducing the area requiring expert inspection by up to 99.8% -- from over 1,000 sq km to less than 2 sq km in some cases. Our method does not rely on labeled training data and offers a scalable first step toward future machine-assisted marine mammal monitoring from space. We have open sourced this pipeline at https://github.com/microsoft/whales.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。