针对无人机拍摄小鸟追踪难题，构建新数据集并提出高效算法。
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
- 利用视频时序信息增强小目标检测与关联能力
- 新数据集含211段视频、10.8万帧标注，覆盖复杂运动场景
- 胜出方案性能比基线提升5.1倍，适用于生态监测等应用
当目标仅占几十像素时，小目标多对象追踪（SMOT）极具挑战，因检测和外观关联不可靠。基于MVA2023 SOD4SB挑战的成功经验，本文推出SMOT4SB挑战，通过利用时间信息克服单帧检测局限。主要贡献包括：(1) 构建了包含211段无人机视频序列、共108,192帧标注的SMOT4SB数据集，涵盖多样真实条件，捕捉相机与目标在三维空间中自由运动带来的运动纠缠；(2) 提出SO-HOTA新评估指标，结合点距离与HOTA，降低基于IoU指标对微小位移的敏感性；(3) 举办2025年MVA挑战赛，吸引78名参与者提交308份方案，最优方法相比基线性能提升5.1倍。本工作为无人机场景下的小目标追踪发展奠定基础，应用于防鸟击、农业、渔业及生态监测。
原文摘要 · Abstract (English)
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper introduces the SMOT4SB challenge, which leverages temporal information to address limitations of single-frame detection. Our three main contributions are: (1) the SMOT4SB dataset, consisting of 211 UAV video sequences with 108,192 annotated frames under diverse real-world conditions, designed to capture motion entanglement where both camera and targets move freely in 3D; (2) SO-HOTA, a novel metric combining Dot Distance with HOTA to mitigate the sensitivity of IoU-based metrics to small displacements; and (3) a competitive MVA2025 challenge with 78 participants and 308 submissions, where the winning method achieved a 5.1x improvement over the baseline. This work lays a foundation for advancing SMOT in UAV scenarios with applications in bird strike avoidance, agriculture, fisheries, and ecological monitoring.
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。