CHIRP数据集：面向野外鸟类种群的长期、个体级行为监测
CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild
提供了一个面向野外鸟类长期行为监测的多任务数据集（CHIRP）和基于彩色腿环分割分类的个体重识别流程（CORVID），其应用导向评测（如取食率、共现率）为视觉模型在真实生态场景中的效用评估提供了可借鉴的范式。
原文依据 we introduce such a dataset (CHIRP) with a new method (CORVID) for individual re-identification of wild birds
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论对个体动物进行长期行为监测对于研究不同时间尺度上发生的行为变化至关重要，尤其是在保护生物学和进化生物学领域。计算机视觉方法已被证明有益于生物多样性监测，但野生种群中的自动化行为监测仍然具有挑战性。这源于缺乏涵盖一系列计算机视觉任务的数据集，而这些任务是提取个体动物具有生物学意义的测量所必需的。在此，我们引入了这样一个数据集（CHIRP）以及一种用于野生鸟类个体重识别的新方法（CORVID）。CHIRP（Combining beHaviour, Individual Re-identification and Postures）数据集整理自瑞典拉普兰地区长期研究的野生西伯利亚松鸦种群，支持重识别（re-id）、动作识别、2D关键点估计、目标检测和实例分割。除了传统的任务特定基准测试外，我们还引入了应用特定的基准测试，使用具有生物学意义的指标（取食率、共现率）来评估模型在真实世界用例中的性能。最后，我们提出了CORVID（COlouR-based Video reID），一种基于彩色腿环分割和分类的鸟类个体识别新流程，彩色腿环是视觉识别个体鸟类的广泛使用方法。CORVID通过将检测到的彩色腿环组合与数据库匹配，提供了一种基于概率的身份跟踪方法。我们使用应用特定的基准测试表明，CORVID优于最先进的重识别方法。我们希望这项工作为社区提供一个蓝图，用于整理来自伦理批准的生物学研究的真实世界数据集，以弥合计算机视觉研究与生物学应用之间的差距。
英文原文摘要 1831 字符
Long-term behavioral monitoring of individual animals is crucial for studying behavioral changes that occurs over different time scales, especially for conservation and evolutionary biology. Computer vision methods have proven to benefit biodiversity monitoring, but automated behavior monitoring in wild populations remains challenging. This stems from the lack of datasets that cover a range of computer vision tasks necessary to extract biologically meaningful measurements of individual animals. Here, we introduce such a dataset (CHIRP) with a new method (CORVID) for individual re-identification of wild birds. The CHIRP (Combining beHaviour, Individual Re-identification and Postures) dataset is curated from a long-term population of wild Siberian jays studied in Swedish Lapland, supporting re-identification (re-id), action recognition, 2D keypoint estimation, object detection, and instance segmentation. In addition to traditional task-specific benchmarking, we introduce application-specific benchmarking with biologically relevant metrics (feeding rates, co-occurrence rates) to evaluate the performance of models in real-world use cases. Finally, we present CORVID COlouR-based Video reID), a novel pipeline for individual identification of birds based on the segmentation and classification of colored leg rings, a widespread approach for visual identification of individual birds. CORVID offers a probability-based id tracking method by matching the detected combination of color rings with a database. We use application-specific benchmarking to show that CORVID outperforms state of the art re-id methods. We hope this work offers the community a blueprint for curating real-world datasets from ethically approved biological studies to bridge the gap between computer vision research and biological applications.