ATARS：一个空中交通原子活动识别与时间分割数据集
ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset
AI总结：
针对现有交通原子活动数据集视角受限、仅含视频级标注的问题，该研究推出首个航拍多标签ATARS数据集，提出多标签时间原子活动识别新任务，实验验证了数据集的独特挑战并给出未来研究方向。
摘要：
交通原子活动描述拓扑交叉口动态的交通模式，是智能驾驶系统发展中的关键课题。然而，现有原子活动数据集均以自车视角采集，无法支撑需要获取整个交叉口交通活动的场景。此外，现有数据集仅提供视频级的原子活动标注，需要耗费大量精力手动裁剪视频以开展识别任务，也限制了其在未裁剪视频上的应用。为填补这一空白，我们推出了空中交通原子活动识别与分割（ATARS）数据集，这是首个专为多标签原子活动分析设计的航拍数据集。我们为每一帧都提供了原子活动标签，可精准记录交通活动的时间区间。此外，我们提出了一项新任务：多标签时间原子活动识别，该任务能够支撑原子活动精准时间定位的研究，同时减轻识别任务中手动裁剪视频的负担。我们开展了大量实验，在原子活动识别和时间原子活动分割两个任务上评估了现有最先进（SOTA）模型的性能。结果凸显了我们的ATARS数据集所带来的独特挑战，比如识别极小物体的活动。我们进一步开展了全面讨论以分析这些挑战，并为提升航拍视角下原子活动识别效果的未来研究方向提供了有价值的见解。我们的源代码和数据集可在https://github.com/magecliff96/ATARS/ 获取。
英文摘要：
Traffic Atomic Activity which describes traffic patterns for topological intersection dynamics is a crucial topic for the advancement of intelligent driving systems. However, existing atomic activity datasets are collected from an egocentric view, which cannot support the scenarios where traffic activities in an entire intersection are required. Moreover, existing datasets only provide video-level atomic activity annotations, which require exhausting efforts to manually trim the videos for recognition and limit their applications to untrimmed videos. To bridge this gap, we introduce the Aerial Traffic Atomic Activity Recognition and Segmentation (ATARS) dataset, the first aerial dataset designed for multi-label atomic activity analysis. We offer atomic activity labels for each frame, which accurately record the intervals for traffic activities. Moreover, we propose a novel task, Multi-label Temporal Atomic Activity Recognition, enabling the study of accurate temporal localization for atomic activity and easing the burden of manual video trimming for recognition. We conduct extensive experiments to evaluate existing state-of-the-art models on both atomic activity recognition and temporal atomic activity segmentation. The results highlight the unique challenges of our ATARS dataset, such as recognizing extremely small objects' activities. We further provide comprehensive discussion analyzing these challenges and offer valuable insights for future direction to improve recognizing atomic activity in aerial view. Our source code and dataset are available at https://github.com/magecliff96/ATARS/
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。
