Lane-wise Traffic Anomaly Dataset
收藏资源简介:
该数据集由普渡大学电气与计算机工程系、计算机科学系和信息与计算机技术系的学者合作创建。数据集包含来自印第安纳州高速公路监控摄像头的73139个车道级样本,样本被标注为四类专家验证的异常:三种交通相关异常(车道阻塞和恢复、异物入侵和持续拥堵)和一种传感器相关异常(摄像头角度变化)。数据集为每个车道提供结构化时间序列信号,支持车道和道路异常检测。数据集旨在解决实际智能交通系统中低成本、可扩展的车道级异常检测问题。
This dataset was collaboratively developed by researchers from the Department of Electrical and Computer Engineering, Department of Computer Science, and Department of Information and Computer Technology at Purdue University. It contains 73,139 lane-level samples collected from highway surveillance cameras in Indiana, with each sample annotated into four categories of expert-validated anomalies: three traffic-related anomalies (lane blockage and recovery, foreign object intrusion, and sustained congestion) and one sensor-related anomaly (camera angle shift). The dataset provides structured time-series signals for each lane to support lane-level and road anomaly detection tasks. It is designed to address the low-cost, scalable lane-level anomaly detection challenges in real-world intelligent transportation systems (ITS).

- 1Lane-Wise Highway Anomaly Detection普渡大学 · 2025年



