arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.09663cs.CV
收藏

长时间视频中的自监督动物识别

Self-Supervised Animal Identification for Long Videos

University of Bristol(布里斯托大学)

Xuyang Fang, Sion Hannuna, Edwin Simpson, Neill Campbell

AI总结:

本研究提出了一种高效的自监督方法,通过全局聚类任务实现长时间视频中动物个体的高精度识别,准确率超过97%,且内存消耗低,适用于资源受限环境。

摘要:

在长时间视频中识别个体动物对于行为生态、野生动物监测和牲畜管理至关重要。传统方法需要大量的手动标注,而现有的自监督方法计算成本高且不适合长序列,因为内存限制和时间误差传播问题。我们提出了一种高效、自监督的方法,将动物识别重新表述为全局聚类任务,而不是顺序跟踪问题。我们的方法假设单个视频中已知的固定数量的个体——这是实践中常见的场景,并且只需要边界框检测和总数量。通过采样帧对,使用冻结的预训练主干网络,并采用匈牙利算法进行批次伪标签分配的自启动机制,我们的方法在没有身份标签的情况下学习了判别性特征。我们采用了来自视觉-语言模型的二元交叉熵损失,实现了超过97%的准确率,同时消耗的GPU内存每批次少于1GB——比标准对比方法少一个数量级。在具有挑战性的现实数据集(3D-POP鸽子和8头小牛进食视频)上评估,我们的框架与监督基线相匹配或超过,这些基线在超过1000个标注帧上训练。这有效地消除了手动标注的瓶颈。本工作使在消费级硬件上实现高精度的动物识别成为可能,在资源受限的研究环境中具有广泛的应用前景。本文所写的所有代码都在https://huggingface.co/datasets/tonyFang04/8-calves处。

英文摘要:

Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods require extensive manual annotation, while existing self-supervised approaches are computationally demanding and ill-suited for long sequences due to memory constraints and temporal error propagation. We introduce a highly efficient, self-supervised method that reframes animal identification as a global clustering task rather than a sequential tracking problem. Our approach assumes a known, fixed number of individuals within a single video -- a common scenario in practice -- and requires only bounding box detections and the total count. By sampling pairs of frames, using a frozen pre-trained backbone, and employing a self-bootstrapping mechanism with the Hungarian algorithm for in-batch pseudo-label assignment, our method learns discriminative features without identity labels. We adapt a Binary Cross Entropy loss from vision-language models, enabling state-of-the-art accuracy ($>$97\%) while consuming less than 1 GB of GPU memory per batch -- an order of magnitude less than standard contrastive methods. Evaluated on challenging real-world datasets (3D-POP pigeons and 8-calves feeding videos), our framework matches or surpasses supervised baselines trained on over 1,000 labeled frames, effectively removing the manual annotation bottleneck. This work enables practical, high-accuracy animal identification on consumer-grade hardware, with broad applicability in resource-constrained research settings. All code written for this paper are \href{https://huggingface.co/datasets/tonyFang04/8-calves}{here}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑