3.1. Simulation dataset Livox Simu dataset v1.0 EN
Introduction:
The Livox simulation data set is based on the point cloud data and corresponding annotation generated by the autopilot simulation test platform, which supports 3D object detection and semantic segmentation tasks. The sensor is configured with 5 Horizon lidars and 1 Tele-15 ultra long-range lidar. The entire data set contains 14445 frames of 360 ° Lidar point cloud data, 3D bounding box labels for 6 kinds of targets and 14 kinds of point cloud semantic labels. The data set scenarios for this open download are mainly urban wide road scenarios, including two-way 12 lane and two-way 8 lane. Accordingly, the simulation scene also includes a variety of vehicle and pedestrian models, as well as traffic flow simulation closer to the real scene. In addition, the rich traffic lights, traffic signs, isolators (including isolation railings, green belts, isolation piers, etc.), trees and buildings all make the entire simulation scene closer to the actual driving conditions.
Example of simulation scenario:
Examples of dimensions:
Data format and download link:
Please read these terms carefully before downloading the dataset. By downloading or using a dataset, you accept these terms:
GNU General Public License v3.0
Dataset Description Document
data set
Dataset Rosbag
Target detection cases:
Livox_detection_simu