Multi-V2X

Multi-V2X is a large-scale, multi-modal, multi-penetration-rate dataset for cooperative perception under vehicle-to-everything (V2X) environment. Multi-V2X is gathered by SUMO-CARLA co-simulation and supports tasks including 3D object detection and tracking. Multi-V2X provides RGB images, point cloud from CAV and RSU with various CAV penetration rates (up to 86%).Multi-V2X是一款面向车万物互联（Vehicle-to-Everything, V2X）环境下协同感知任务的大规模多模态多渗透率数据集。该数据集依托SUMO与CARLA联合仿真构建，可支持三维目标检测与跟踪等相关任务。数据集提供不同联网自动驾驶车辆（Connected and Automated Vehicle, CAV）渗透率（最高达86%）场景中，由车载联网自动驾驶车辆与路侧单元（Road Side Unit, RSU）采集的RGB图像及点云数据。

搜集汇总

背景与挑战

背景概述

Multi-V2X是一个大规模、多模态的车联网协同感知数据集，通过SUMO-CARLA仿真生成，包含来自CAV和RSU的RGB图像与点云数据，支持3D目标检测和跟踪任务，并覆盖多种道路类型及CAV渗透率。