ECMD：一个面向SLAM的以事件为中心的多传感器驾驶数据集
ECMD: An Event-Centric Multisensory Driving Dataset for SLAM
AI总结：
本文提出面向SLAM的ECMD多传感器驾驶数据集，含81个序列、超200公里复杂场景，配备多类传感器与厘米级真值，还评估了主流SLAM算法的性能局限。
摘要：
利用多类传感器可增强对复杂环境的感知能力，提升对不同光照条件和高速运动模式的鲁棒性，从而实现精准的定位与建图。本文提出了ECMD，一个以事件为中心的多传感器数据集，包含81个序列，覆盖超过200公里的各类高难度驾驶场景，包括高速运动、重复场景、动态物体等。ECMD提供了两组不同分辨率（640*480、346*260）的立体事件相机、立体工业相机、一台红外相机、一台顶部安装的机械激光雷达搭配两台倾斜激光雷达、两台消费级GNSS接收机以及一台车载IMU的数据。同时，车辆的真值数据通过厘米级高精度GNSS-RTK/INS导航系统获取。所有传感器均经过良好校准，并在硬件层面实现时间同步，可同时记录数据。我们还评估了若干当前最优的SLAM算法，用于为视觉和激光雷达SLAM提供基准，并明确其局限性。该数据集可在https://arclab-hku.github.io/ecmd/ 获取。
英文摘要：
Leveraging multiple sensors enhances complex environmental perception and increases resilience to varying luminance conditions and high-speed motion patterns, achieving precise localization and mapping. This paper proposes, ECMD, an event-centric multisensory dataset containing 81 sequences and covering over 200 km of various challenging driving scenarios including high-speed motion, repetitive scenarios, dynamic objects, etc. ECMD provides data from two sets of stereo event cameras with different resolutions (640*480, 346*260), stereo industrial cameras, an infrared camera, a top-installed mechanical LiDAR with two slanted LiDARs, two consumer-level GNSS receivers, and an onboard IMU. Meanwhile, the ground-truth of the vehicle was obtained using a centimeter-level high-accuracy GNSS-RTK/INS navigation system. All sensors are well-calibrated and temporally synchronized at the hardware level, with recording data simultaneously. We additionally evaluate several state-of-the-art SLAM algorithms for benchmarking visual and LiDAR SLAM and identifying their limitations. The dataset is available at https://arclab-hku.github.io/ecmd/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
