HRHD-HK：用于摄影测量点云三维语义分割的高层高密度城市场景基准数据集
HRHD-HK: A benchmark dataset of high-rise and high-density urban scenes for 3D semantic segmentation of photogrammetric point clouds
AI总结：
本文构建首个面向高层高密度城区的摄影测量点云基准HRHD-HK，并评估八种语义分割方法，揭示现有方法在小体积城市对象上的不足。
摘要：
许多现有的三维语义分割方法，尤其是计算机视觉中的深度学习方法，声称已在城市点云上取得理想效果。因此，在包含高层、低层、高密度和低密度城区的多样化真实城市场景中定量评估这些方法具有重要意义。然而，现有公共基准数据集主要呈现欧洲城市的低层场景，无法全面评估相关方法。本文提出一个高层城市点云基准数据集，即香港高层、高密度城市场景（HRHD-HK）。HRHD-HK按150个瓦片组织，包含来自多样城市环境的2.73亿个彩色摄影测量三维点。其语义标签包括建筑、植被、道路、水体、设施、地形和车辆。据我们所知，HRHD-HK是首个聚焦高层高密度城区的摄影测量数据集。本文还在HRHD-HK数据集上综合评估了八种流行的语义分割方法。实验结果证实，当前点云三维语义分割仍有很大提升空间，尤其是小体积城市对象。我们的数据集公开发布于 https://doi.org/10.25442/hku.23701866.v2。
英文摘要：
Many existing 3D semantic segmentation methods, deep learning in computer vision notably, claimed to achieve desired results on urban point clouds. Thus, it is significant to assess these methods quantitatively in diversified real-world urban scenes, encompassing high-rise, low-rise, high-density, and low-density urban areas. However, existing public benchmark datasets primarily represent low-rise scenes from European cities and cannot assess the methods comprehensively. This paper presents a benchmark dataset of high-rise urban point clouds, namely High-Rise, High-Density urban scenes of Hong Kong (HRHD-HK). HRHD-HK arranged in 150 tiles contains 273 million colorful photogrammetric 3D points from diverse urban settings. The semantic labels of HRHD-HK include building, vegetation, road, waterbody, facility, terrain, and vehicle. To our best knowledge, HRHD-HK is the first photogrammetric dataset that focuses on HRHD urban areas. This paper also comprehensively evaluates eight popular semantic segmentation methods on the HRHD-HK dataset. Experimental results confirmed plenty of room for enhancing the current 3D semantic segmentation of point clouds, especially for city objects with small volumes. Our dataset is publicly available at https://doi.org/10.25442/hku.23701866.v2.
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。
