RELLIS-3D
收藏资源简介:
RELLIS-3D数据集是由德州农工大学机械工程系创建的多模态数据集,专注于非公路环境的语义场景理解。该数据集包含13,556个激光雷达扫描和6,235张图像的标注,数据采集自德州农工大学的Rellis校园。数据集内容丰富,包括颜色相机图像、激光扫描、高精度全球定位测量等,旨在解决非公路环境中自主导航的挑战,如类别不平衡和环境地形复杂性。数据集的创建过程涉及同步传感器数据和精确时间协议(PTP),以确保数据质量。RELLIS-3D数据集的应用领域主要集中在提升非公路环境中的自主导航技术,通过提供丰富的多模态数据和标注,支持研究人员开发更先进的算法和探索新的研究方向。
The RELLIS-3D Dataset is a multimodal dataset created by the Department of Mechanical Engineering at Texas A&M University, focusing on semantic scene understanding for off-road environments. It contains annotations for 13,556 LiDAR scans and 6,235 images, which were collected on the Rellis Campus of Texas A&M University. The dataset features rich content including color camera images, LiDAR scans, high-precision global positioning measurements and more, aiming to address the challenges of autonomous navigation in off-road environments such as class imbalance and complex terrain. The dataset creation process involves synchronized sensor data and the Precision Time Protocol (PTP) to ensure data quality. The main application fields of the RELLIS-3D Dataset center on advancing autonomous navigation technologies in off-road environments. By providing abundant multimodal data and annotations, it supports researchers in developing more advanced algorithms and exploring new research directions.




