新基准DynUAV挑战复杂动态无人机追踪，逼真模拟真实飞行扰动。
Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions
- 构建含剧烈自运动的动态无人机视角追踪数据集
- 覆盖170万标注框，包含车辆、行人及工程设备等多类目标
- 适合研究真实场景下鲁棒多目标追踪算法的团队使用
无人机快速机动带来的显著观测挑战使得多目标追踪（MOT）面临严峻考验。现有无人机视角MOT基准普遍缺乏这些复杂性，多呈现可预测的相机运动和线性运动模式。为此，我们提出DynUAV，一个具有强烈自运动和复杂视差轨迹的动态无人机视角MOT新基准。该基准包含42段视频序列，超过170万条边界框标注，涵盖车辆、行人以及挖掘机、推土机、起重机等特殊工业类别。相比现有基准，DynUAV引入了由自运动引发的剧烈尺度变化、视角突变及运动模糊等重大挑战。对前沿追踪器在该基准上的全面评估揭示其在动态条件下检测与关联协同处理能力的局限性，确立了DynUAV作为严苛测试平台的地位。我们期望它能推动真实场景无人机视角MOT的发展，并将所有资源公开发布。
原文摘要 · Abstract (English)
The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at link.
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。