Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers

By Martin Weinmann, B. Jutzi, Stefan Hinz, Clément Mallet. 2015

672 citations recorded by the source corpus.

Subfields: Computational Mechanics, Environmental Engineering, Geology, Representation & Self-Supervised Learning, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Environmental Engineering

In Geology

In Representation & Self-Supervised Learning

In 3D Vision & Pose

Citations in the corpus

L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving (2019, methodology): “Secondly, we then evaluate the linearity and scattering of each candidate keypoint using the well-known 3D structure tensor [34].”
Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, methodology): “Two most representative and widely-used neighborhood searching methods are k-nearest neighbors (KNN) [12, 96, 99] and spherical neighborhood [100].”
Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs (2017, methodology): “We use adaptive neighborhoods [49] to compensate for variable sampling density.”
Incremental and Enhanced Scanline-Based Segmentation Method for Surface Reconstruction of Sparse LiDAR Data (2016, methodology): “In practical environments, point clouds of dynamic objects, such as pedestrians, can be removed to get a clear reconstruction either by tightening the thresholds of the proposed method or identifying them with the method in [32].”
Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification (2017, methodology): “• classify each point for example by computing local features (hand-made (Weinmann et al., 2015) or by deeplearning methods (Huang and You, 2016)), then group them into objects for example by conditional random field (CRF) methods (see Landrieu et al.”
The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereo (2021, methodology): “For semantic segmentation of the point cloud, we compute geometric features as proposed in Weinmann et al. (2015) and in Chehata et al. (2009) by estimating the structural tensor for a local neighborhood of each point.”