five

Supporting data for "HRHD-HK: A Benchmark Dataset of High-Rise and High-Density Urban Scenes for 3D Semantic Segmentation of Photogrammetric Point Clouds"

收藏
DataCite Commons2023-12-12 更新2025-04-16 收录
下载链接:
https://datahub.hku.hk/articles/dataset/Supporting_data_for_HRHD-HK_A_Benchmark_Dataset_of_High-Rise_and_High-Density_Urban_Scenes_for_3D_Semantic_Segmentation_of_Photogrammetric_Point_Clouds_/23701866/1
下载链接
链接失效反馈
官方服务:
资源简介:
<strong>HRHD-HK: A Benchmark Dataset of High-Rise and High-Density Urban Scenes for 3D Semantic Segmentation of Photogrammetric Point Clouds</strong> This is the official repository of the HRHD-HK dataset. For technical details, please refer to: Li, M., Wu, Y., Yeh, A. G. O., &amp; Xue, F. (2023). HRHD-HK: A benchmark dataset of high-rise and high-density urban scenes for 3D semantic segmentation of photogrammetric point clouds [Preprint]. arXiv:2307.07976. doi: 10.48550/arXiv.2307.07976<br> <strong>Overview of HRHD-HK</strong> This paper presents a benchmark dataset of high-rise hig-density urban point clouds, namely High-Rise, High-Density urban scenes of Hong Kong (HRHD-HK) for 3D semantic segmentation.  The semantic labels of HRHD-HK include 1) building, 2) vegetation, 3) road, 4) waterbody, 5) facility, 6) terrain, and 7) vehicle. Point clouds of HRHD-HK were collected in HK with two features, i.e., color and coordinates in the HK 1980 Grid system (EPSG:2326). HRHD-HK arranged in 150 tiles, contain approximately 273 million points, covering 9.375 km<sup>2</sup>. Each tile of point clouds was saved in the "ply" format with seven channels, i.e., x, y, z, red, green, blue, and label. HRHD-HK aims to supplement the existing benchmark datasets with Asian HRHD urban scenes as well as subtropical natural landscapes, such as sea, vegetation, and mountains. <br> For any inquiries, please feel free to contact Maosu at maosulee@connect.hku.hk or Dr. Frank at xuef@hku.hk. Please cite our paper, if you find our work useful for your research. <br>

**HRHD-HK:面向摄影测量点云(Photogrammetric Point Clouds)三维语义分割(3D Semantic Segmentation)的高密度超高层城市场景基准数据集** 本仓库为HRHD-HK数据集的官方开源仓库。如需获取详细技术信息,请参阅以下论文:Li M、Wu Y、Yeh A G O 与 Xue F 于2023年发布的预印本《HRHD-HK:面向摄影测量点云三维语义分割的高密度超高层城市场景基准数据集》,arXiv编号:2307.07976,DOI:10.48550/arXiv.2307.07976。 **HRHD-HK数据集概览** 本论文提出了一款面向三维语义分割的高密度超高层城市点云基准数据集,即针对中国香港地区超高层高密度城市场景构建的HRHD-HK数据集。 HRHD-HK数据集的语义标签共包含7类,各类标签及其对应英文如下:1)建筑物(building)、2)植被(vegetation)、3)道路(road)、4)水体(waterbody)、5)设施(facility)、6)地形(terrain)、7)车辆(vehicle)。 HRHD-HK的点云数据采集自中国香港地区,包含两类核心特征:色彩信息与香港1980坐标系(EPSG:2326)下的三维坐标信息。 该数据集共划分为150个分块(tiles),总计包含约2.73亿个点云,覆盖总面积达9.375平方千米。 每个分块的点云数据均以PLY(ply)格式存储,包含7个数据通道:x、y、z三维坐标,红(red)、绿(green)、蓝(blue)色彩通道,以及标签(label)通道。 本数据集旨在填补现有基准数据集在亚洲超高层高密度城市场景以及亚热带自然景观(如海域、植被与山地)相关数据方面的空白。 如有任何疑问,可联系Maosu(邮箱:maosulee@connect.hku.hk)或Frank博士(邮箱:xuef@hku.hk)。若本研究对您的科研工作有所帮助,请引用本论文。
提供机构:
HKU Data Repository
创建时间:
2023-07-19
二维码
社区交流群
二维码
科研交流群
商业服务