Signalized INtersection Dataset (SIND)
收藏资源简介:
Signalized INtersection Dataset (SIND)是由北京理工大学机械工程学院创建的一个专门针对信号交叉口的数据集。该数据集包含7小时的记录,涵盖超过13,000个交通参与者(TPs),并详细记录了交通灯状态和违规行为。SIND通过无人机搭载的高清摄像头捕捉数据,特别关注了交通灯状态对交通参与者行为的影响。数据集的应用领域包括自动驾驶中的行为建模、运动预测和安全验证等,旨在解决复杂交通环境下的安全挑战。
The Signalized INtersection Dataset (SIND) was developed by the School of Mechanical Engineering, Beijing Institute of Technology, as a dataset specifically targeting signalized intersections. It contains 7 hours of recorded data, covering over 13,000 traffic participants (TPs), with detailed records of traffic light states and traffic violations. SIND captures data via high-definition cameras mounted on unmanned aerial vehicles (UAVs), with a particular focus on the impact of traffic light states on the behaviors of traffic participants. Application areas of this dataset include behavior modeling, motion prediction, and safety verification in autonomous driving, among others, aiming to address safety challenges in complex traffic environments.

- 1SIND: A Drone Dataset at Signalized Intersection in China北京理工大学机械工程学院 · 2022年



