Wild-Places Dataset

Wild-Places is a large-scale LiDAR dataset for inter and intra-run place recognition in unstructured natural environments. The data was collected in two environments at the Karawatha and Venman walking trails in Brisbane, Australia over fourteen months, allowing for research into both long and short-term revisits. We release sub-maps produced from a global point cloud for four sequences in both environments for a total of ~67K submaps, with accurate 6DoF poses and timestamps for each submap. \nLineage: The data was collected using a handheld sensor payload consisting of a spinning lidar sensor mounted at an angle of 45 degrees to maximise field of view, a motor, encoder, an IMU, and four cameras. For each collected sequence we use the Wildcat slam system to create an accurate 6DoF estimation of the pose of the sensor and to process the lidar data into a globally registered map, from which we produce our submaps.Wild-Places是一款面向非结构化自然环境下跨序列与序列内地点识别的大规模激光雷达（LiDAR）数据集。该数据集于澳大利亚布里斯班的Karawatha与Venman徒步步道两处环境中耗时十四个月采集完成，可支撑长期与短期重访相关研究。我们发布了从全局点云生成的子地图，涵盖两处环境中的四个序列，总计约6.7万个子地图，每个子地图均附带精确的6自由度（6DoF）位姿与时间戳信息。 数据集溯源：本次采集采用手持传感器载荷方案，包含一台以45度角安装以最大化视场的旋转激光雷达传感器、电机、编码器、惯性测量单元（IMU）以及四个摄像头。针对每条采集到的序列，我们使用Wildcat同步定位与建图（SLAM）系统实现传感器位姿的精确6自由度估计，并将激光雷达数据处理为全局配准地图，再从中生成本次发布的子地图。