ALS2DTM
收藏资源简介:
ALS2DTM数据集是由计算机科学与随机系统研究所(IRISA)创建的大型数据集,包含16.59亿个点云数据和相应的数字地形模型(DTM),覆盖面积达52平方公里,涵盖城市、森林和山区等多种场景。该数据集旨在支持深度学习方法在从机载激光扫描(ALS)点云中提取DTM的研究。数据集的创建过程涉及从开放数据源收集点云数据及其对应的DTM,并通过基准方法进行验证。ALS2DTM数据集的应用领域包括地理和环境研究,如洪水建模、地上生物量估计和基础设施规划等,旨在解决从复杂地形中准确提取DTM的问题。
The ALS2DTM dataset is a large-scale dataset developed by the Institute of Computer Science and Random Systems (IRISA). It contains 1.659 billion point cloud samples and their corresponding Digital Terrain Models (DTM), spanning an area of 52 square kilometers and covering diverse scenarios including urban, forested, and mountainous regions. This dataset is intended to support research on deep learning-based methods for extracting Digital Terrain Models from Airborne Laser Scanning (ALS) point clouds. The development of the ALS2DTM dataset involves collecting point cloud data and their matched DTMs from open data sources, followed by validation using benchmark approaches. Application areas of the ALS2DTM dataset cover geographic and environmental research, such as flood modeling, above-ground biomass estimation, infrastructure planning and other related fields, aiming to address the challenge of accurately extracting DTMs from complex terrains.

- 1Learning Digital Terrain Models from Point Clouds: ALS2DTM Dataset and Rasterization-based GAN计算机科学与随机系统研究所(IRISA) · 2022年



