构建首个异构激光雷达车联网数据集，支持多车协同感知研究。
Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration
- 采集三辆自动驾驶车与路侧单元的多配置激光雷达点云。
- 含45.1万帧点云、240.6万个标注框，覆盖10类目标。
- 专为异构传感器协同感知设计，适合自动驾驶算法验证。
车联网协同感知成为突破单车感知局限的有力方案，但现有数据集在规模、多样性与质量上均存在不足。为此，我们提出Mixed Signals数据集，包含来自三辆联网自动驾驶车辆（配备两种不同配置的激光雷达）及一个双激光雷达路侧单元采集的45.1万帧点云和240.6万个边界框标注。数据涵盖10类目标，具备精确的时间对齐与一致标注，支持可靠感知模型训练。我们提供了详尽的数据质量分析，并在此数据集上广泛评估了现有车联网方法。该数据集已可直接使用，官网地址为https://mixedsignalsdataset.cs.cornell.edu/。
原文摘要 · Abstract (English)
Vehicle-to-everything (V2X) collaborative perception has emerged as a promising solution to address the limitations of single-vehicle perception systems. However, existing V2X datasets are limited in scope, diversity, and quality. To address these gaps, we present Mixed Signals, a comprehensive V2X dataset featuring 45.1k point clouds and 240.6k bounding boxes collected from three connected autonomous vehicles (CAVs) equipped with two different configurations of LiDAR sensors, plus a roadside unit with dual LiDARs. Our dataset provides point clouds and bounding box annotations across 10 classes, ensuring reliable data for perception training. We provide detailed statistical analysis on the quality of our dataset and extensively benchmark existing V2X methods on it. The Mixed Signals dataset is ready-to-use, with precise alignment and consistent annotations across time and viewpoints. Dataset website is available at https://mixedsignalsdataset.cs.cornell.edu/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。