Journal of Applied Remote Sensing · 2021 · 21 citations · 21 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningNearest Neighbor SearchPhotogrammetryPoint Cloud ProcessingScene ClassificationFeature Extraction From Lidar DataIndexingLight Detection And Ranging Point Cloud AcquisitionNeighbor Search AlgorithmsPoint Cloud ClassificationPoint Cloud Feature ExtractionPoint Cloud FeaturesUrban Scene Interpretation
Mobile laser scanning (MLS), which can quickly collect a high-resolution and highprecision point cloud of the surroundings of a vehicle, is an appealing technology for threedimensional (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 F 1 score, whereas it uses simpler geometric features derived from a spherical neighborhood with a radius of 0.5 m.
21
DIMENSIONALITY BASED SCALE SELECTION IN 3D LIDAR POINT CLOUDS
Jérôme Demantke, Clément Mallet, Nicolás David et al. · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · 2012 · 365 citations · Full text