OPV2V
收藏资源简介:
OPV2V是第一个使用V2V通信进行感知的大规模开放数据集。通过使用名为OpenCDA和CARLA simulator的合作驾驶共同仿真框架,我们收集了具有各种数量的连接车辆的不同场景,以涵盖具有挑战性的驾驶情况,例如严重的遮挡。 主要特点: 来自多连接自动车辆的聚合传感器数据 73个场景、6个道路类型、9个城市 12k帧LiDAR点云和RGB相机图像,230K注释3D边界框 具有4个激光雷达探测器和4种不同融合策略的综合基准 (共16个模型)
OPV2V is the first large-scale open dataset for perception using vehicle-to-vehicle (V2V) communication. By leveraging the cooperative driving co-simulation framework named OpenCDA and CARLA Simulator, we collected diverse scenarios with varying numbers of connected vehicles to cover challenging driving situations such as severe occlusions. Key Features: - Aggregated sensor data from multiple connected automated vehicles - 73 scenarios, 6 road types, and 9 urban cities - 12k frames of LiDAR point clouds and RGB camera images, with 230k annotated 3D bounding boxes - Comprehensive benchmarks with 4 LiDAR detectors and 4 distinct fusion strategies, totaling 16 models




