万集路侧交通参与者轨迹数据集

万集交通轨迹数据集来源于真实交通场景，融合了多路路侧激光雷达融合点云数据和相机视频数据，对真实交通场景中每一个交通参与者运动过程的三维信息进行时序数据采样。针对连续帧点云数据，标注包括目标ID，采样时间，目标位置，形状大小，航向角，交通信号灯状态等信息。 轨迹数据集信息 轨迹数据信息主要包括目标基本信息、车辆驾驶行为、行人/非机动车行为、交通参与者交互行为： 1、目标基本信息主要包括目标id、类别、航向角、速度、加速度、相对坐标等； 2、车辆驾驶行为包括停止、直行、左转、右转、变道、掉头等； 3、行人/非机动车行为包括停止、运动等； 4、交通参与者交互行为主要有车车交互、人车交互等，包括直行-右转碰撞、邻车直行碰撞、对向直行碰撞、鬼探头碰撞、左转-直行碰撞等。

The Wanji Traffic Trajectory Dataset is derived from real traffic scenarios. It fuses multi-channel roadside LiDAR point cloud data and camera video data, and performs temporal data sampling on the 3D information of the movement process of every traffic participant in real traffic scenarios. For consecutive frame point cloud data, the annotations include target ID, sampling time, target position, shape and size, heading angle, traffic light status and other information.

Trajectory Dataset Information
The trajectory data mainly includes target basic information, vehicle driving behaviors, pedestrian/non-motor vehicle behaviors, and interactive behaviors of traffic participants:
1. Target basic information mainly includes target ID, category, heading angle, velocity, acceleration, relative coordinates and other information;
2. Vehicle driving behaviors include stopping, going straight, turning left, turning right, lane changing, U-turn and other behaviors;
3. Pedestrian/non-motor vehicle behaviors include stopping, moving and other behaviors;
4. Interactive behaviors of traffic participants mainly include vehicle-vehicle interaction, vehicle-pedestrian interaction and other scenarios, including straight-right turn collision, adjacent vehicle straight-going collision, oncoming straight-going collision, ghost probe collision, left turn-straight collision and other collision scenarios.

搜集汇总

背景与挑战

背景概述

万集路侧交通参与者轨迹数据集是一个来源于真实交通场景的数据集，融合了多路路侧激光雷达和相机视频数据，标注了交通参与者的三维时序信息。该数据集适用于交通物流领域，可用于微观交通模型仿真、驾驶行为分析和自动驾驶算法开发验证等多种应用场景。