Pointwise classification of mobile laser scanning point clouds of urban scenes using raw data
Pointwise classification of mobile laser scanning point clouds of urban scenes using raw data
复制标题
使用原始数据对城市场景移动激光扫描点云进行逐点分类
DOI：
10.1117/1.jrs.15.024523
复制
发表时间：
2021-06-29
影响因子：
1.7
通讯作者：
Liu, Xu
中科院分区：
文献类型：
--
作者：
Li, Qiujie;Yuan, Pengcheng;Liu, Xu
抽象的。移动激光扫描(MLS)技术能够快速采集车辆周围高分辨率、高精度的点云，是城市三维场景分析的一种很有吸引力的技术。在这方面，多层最小二乘点云的分类是一项常见的核心任务。我们的重点是逐点分类，通过应用二进制分类器将每个单独的点分类到一个特定的类中，该分类器涉及一组从点的邻域派生的局部特征。为了加快逐点分类的邻域搜索速度和增强特征的区分性，我们利用光检测和测距(LiDAR)获得的原始数据中的拓扑和语义信息，并按扫描顺序记录。首先，恢复用于数据索引的二维(2D)扫描网格，并计算相对于LiDAR位置的相对3D坐标。随后，使用一种高效的邻域搜索方法提取一组局部特征，该方法具有与点云中的点数无关的低计算复杂度。通过结合决策树的GentleBoost监督学习算法，这些特征被进一步合并，以产生用于特定类别的各种二进制分类器。在paris-rue-cassette数据库上的实验结果表明，该方法比现有的方法在F1评分上有10%的改进，而它使用了更简单的几何特征，该特征来自半径为0.5m的球面邻域。
Abstract. Mobile laser scanning (MLS), which can quickly collect a high-resolution and high-precision point cloud of the surroundings of a vehicle, is an appealing technology for three-dimensional (3D) urban scene analysis. In this regard, the classification of MLS point clouds is a common and core task. We focus on pointwise classification, in which each individual point is categorized into a specific class by applying a binary classifier involving a set of local features derived from the neighborhoods of the point. To speed up the neighbor search and enhance feature distinctiveness for pointwise classification, we exploit the topological and semantic information in the raw data acquired by light detection and ranging (LiDAR) and recorded in scan order. First, a two-dimensional (2D) scan grid for data indexing is recovered, and the relative 3D coordinates with respect to the LiDAR position are calculated. Subsequently, a set of local features is extracted using an efficient neighbor search method with a low computational complexity independent of the number of points in a point cloud. These features are further merged to produce a variety of binary classifiers for specific classes via a GentleBoost supervised learning algorithm combining decision trees. The experimental results on the Paris-rue-Cassette database demonstrate that the proposed approach outperforms the state-of-the-art methods with a 10% improvement in the F1 score, whereas it uses simpler geometric features derived from a spherical neighborhood with a radius of 0.5 m.