Shape-based recognition of 3D point clouds in urban environments

This paper investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The system is decomposed into four steps: locating, segmenting, characterizing, and classifying clusters of 3D points. Specifically, we first cluster nearby points to form a set of potential object locations (with hierarchical clustering). Then, we segment points near those locations into foreground and background sets (with a graph-cut algorithm). Next, we build a feature vector for each point cluster (based on both its shape and its context). Finally, we label the feature vectors using a classifier trained on a set of manually labeled objects. The paper presents several alternative methods for each step. We quantitatively evaluate the system and tradeoffs of different alternatives in a truthed part of a scan of Ottawa that contains approximately 100 million points and 1000 objects of interest. Then, we use this truth data as a training set to recognize objects amidst approximately 1 billion points of the remainder of the Ottawa scan.

• Publication year

  2009

• Venue

  IEEE International Conference on Computer Vision

• Publication date

  2009-09-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/ICCV.2009.5459471
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Fast Surface Reconstruction and Segmentation with Ground-Based and Airborne LIDAR Range Data

  2009cited by this paper
• Architectural Modeling from Sparsely Scanned Range Data

  2008cited by this paper
• Building reconstruction from a single DEM

  2008cited by this paper
• A Lidar Point Cloud Based Procedure for Vertical Canopy Structure Analysis And 3D Single Tree Modelling in Forest

  2008cited by this paper
• Retrieval Algorithms for Road Surface Modelling Using Laser-Based Mobile Mapping

  2008cited by this paper
• A Comprehensive Automated 3D Approach for Building Extraction, Reconstruction, and Regularization from Airborne Laser Scanning Point Clouds

  2008cited by this paper
• Knowledge and heuristic-based modeling of laser-scanned trees

  2007cited by this paper
• Building Outline Extraction from Digital Elevation Models Using Marked Point Processes

  2007cited by this paper
• Production Friendly Character Skinning

  2007cited by this paper
• Conditional Random Field for 3D Point Clouds with Adaptive Data Reduction

  2007cited by this paper
• 3D Building Reconstruction with Parametric Roof Superstructures

  2007cited by this paper
• Rapid and scalable 3D object recognition using LIDAR data

  2006cited by this paper
• Improving the Realism of Existing 3D City Models

  2006cited by this paper
• Rapid object indexing using locality sensitive hashing and joint 3D-signature space estimation

  2006cited by this paper
• Graph Cuts and Efficient N-D Image Segmentation

  2006cited by this paper
• SEGMENTATION OF POINT CLOUDS USING SMOOTHNESS CONSTRAINT

  2006cited by this paper
• Natural terrain classification using three‐dimensional ladar data for ground robot mobility

  2006cited by this paper
• Segmentation of point clouds using smoothness constraints

  2006cited by this paper
• Scale selection for classification of point-sampled 3D surfaces

  2005cited by this paper
• Data Processing Algorithms for Generating Textured 3D Building Facade Meshes from Laser Scans and Camera Images

  2005cited by this paper
• Autonomous Terrain Mapping and Classification Using Hidden Markov Models

  2005cited by this paper
• Discriminative learning of Markov random fields for segmentation of 3D scan data

  2005cited by this paper
• Recognizing Objects in Range Data Using Regional Point Descriptors

  2004cited by this paper
• Urban Site Modeling from LiDAR

  2003cited by this paper
• Robust extraction of multiple structures from non-uniformly sampled data

  2003cited by this paper
• Shape Context: A New Descriptor for Shape Matching and Object Recognition

  2000cited by this paper
• Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes

  1999cited by this paper
• Normalized cuts and image segmentation

  1997cited by this paper
• The estimation of the gradient of a density function, with applications in pattern recognition

  1975influential reference

• A Survey on Edge-Aware Graph Learning Methods

  2026cites this paper
• A Semantic-Associated Factor Graph Model for LiDAR-Assisted Indoor Multipath Localization

  2026cites this paper
• Generating Adversarial Point Clouds Using Diffusion Model

  2025cites this paper
• Embrace descriptors that use point pairs feature

  2024cites this paper
• Integrity with LiDAR Incorrect Extraction Faults in Adverse Weather Conditions

  2024cites this paper
• Point Cloud Classification via Deep Set Linearized Optimal Transport

  2024cites this paper
• Memory-Augmented 3D Point Cloud Semantic Segmentation Network for Intelligent Mining Shovels

  2024cites this paper
• Point Cloud Semantic Segmentation by Adaptively Fusing Information With Varying Distances

  2024cites this paper
• On efficient 3D object retrieval

  2024cites this paper
• PointDMM: A Deep-Learning-Based Semantic Segmentation Method for Point Clouds in Complex Forest Environments

  2023cites this paper
• PCTN: Point cloud data transformation network

  2023cites this paper
• UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation

  2023cites this paper
• 3D point cloud descriptors: state-of-the-art

  2023cites this paper
• Strict rule-based automatic training data extraction using Mobile laser scanning in urban area

  2023cites this paper
• DETECTION AND SEGMENTATION OF POLE-LIKE OBJECTS IN MOBILE LASER SCANNING POINT CLOUDS

  2023cites this paper
• Multi feature-rich synthetic colour to improve human visual perception of point clouds

  2023cites this paper
• Using the Transferable Belief Model for Object Classification in LiDAR Data With Geometry, Motion and Context Features

  2023cites this paper
• Vision-based mobile analysis of roadside guardrail structures

  2023cites this paper
• A Refined Extraction Method for Street Trees in Mobile Laser System Point Clouds

  2023cites this paper
• DNN-Based Map Deviation Detection in LiDAR Point Clouds

  2023cites this paper
• Integrity with Extraction Faults in LiDAR-Based Urban Navigation for Driverless Vehicles

  2023cites this paper
• Instance-Aware Semantic Segmentation of Road Furniture in Mobile Laser Scanning Data

  2022cites this paper
• Moving objects extraction for building environmental maps describing human walking activity using a 3D LiDAR

  2022cites this paper
• IAGC: Interactive Attention Graph Convolution Network for Semantic Segmentation of Point Clouds in Building Indoor Environment

  2022cites this paper
• Cluster-Based Autoencoders for Volumetric Point Clouds

  2022cites this paper
• Performance boosting of conventional deep learning-based semantic segmentation leveraging unsupervised clustering

  2022cites this paper
• Fully Automated Algorithm for Light Pole Detection and Mapping in Rural Highway Environment Using Mobile Light Detection and Ranging Point Clouds

  2022cites this paper
• A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

  2022cites this paper
• AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

  2022cites this paper
• A segment-based filtering method for mobile laser scanning point cloud

  2022cites this paper
• MBBOS-GCN: minimum bounding box over-segmentation—graph convolution 3D point cloud deep learning model

  2022cites this paper
• 3D Point Clouds Reconstruction of Environment Subject to Thin Structures

  2022cites this paper
• Context Extraction from GIS Data Using LiDAR and Camera Features

  2022cites this paper
• LiDAR Filtering in 3D Object Detection Based on Improved RANSAC

  2022cites this paper
• GAPointNet: Graph attention based point neural network for exploiting local feature of point cloud

  2021cites this paper
• Toward Building and Civil Infrastructure Reconstruction From Point Clouds: A Review on Data and Key Techniques

  2021cites this paper
• Visualization of 3D cable between utility poles obtained from laser scanning point clouds: a case study

  2021cites this paper
• Point Cloud Inversion: A Novel Approach for the Localization of Trees in Forests from TLS Data

  2021cites this paper
• A voxelized point clouds representation for object classification and segmentation on 3D data

  2021cites this paper
• A Geometry Feature Aggregation Method for Point Cloud Classification and Segmentation

  2021cites this paper
• Automatic Extraction and Labelling of Memorial Objects From 3D Point Clouds

  2021cites this paper
• A Hierarchical Approach for Point Cloud Classification With 3D Contextual Features

  2021cites this paper
• Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification

  2021cites this paper
• Learning 3D Semantic Segmentation with only 2D Image Supervision

  2021cites this paper
• Segmentation of point clouds via joint semantic and geometric features for 3D modeling of the built environment

  2021cites this paper
• An automatic hybrid method for ground filtering in mobile laser scanning data of various types of roadway environments

  2021cites this paper
• Landmark Attribute Analysis for a High-Precision Landmark-Based Local Positioning System

  2021cites this paper
• Automatic Extraction of Roadside Traffic Facilities From Mobile Laser Scanning Point Clouds Based on Deep Belief Network

  2021cites this paper
• Control of Building Components by Building Information Modeling Technology and 3D Laser Scanning İntegration Technique for Sustainable Building Quality

  2021cites this paper
• Joining Street-View Images and Building Footprint GIS Data

  2021cites this paper
• Self-Supervised Few-Shot Learning on Point Clouds

  2020cites this paper
• Segmentation of unbalanced and in-homogeneous point clouds and its application to 3D scanned trees

  2020cites this paper
• Efficient streaming of 3D maps for unmanned navigation: 3D tiling the navigable space and eliminating occluded geometry

  2020cites this paper
• Down-Sampling of Large LiDAR Dataset in the Context of Off-Road Objects Extraction

  2020cites this paper
• Local Grid Rendering Networks for 3D Object Detection in Point Clouds

  2020cites this paper
• Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study

  2020cites this paper
• Tropical Tree Species 3D Modelling and Classification Based on LiDAR Technology

  2020cites this paper
• Are We Hungry for 3D LiDAR Data for Semantic Segmentation?

  2020cites this paper
• Transfer Learning in urban object classification: Online images to recognize point clouds

  2020cites this paper
• Automatic object recognition within point clouds in clustered or scattered scenes

  2020influential citation
• SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

  2020cites this paper
• Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification

  2020cites this paper
• Three-Dimensional Point Cloud Object Detection Using Scene Appearance Consistency Among Multi-View Projection Directions

  2020cites this paper
• Lidar Data Reduction for Unmanned Systems Navigation in Urban Canyon

  2020cites this paper
• FPConv: Learning Local Flattening for Point Convolution

  2020cites this paper
• Geometric Primitives in LiDAR Point Clouds: A Review

  2020cites this paper
• Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks

  2020cites this paper
• A Convolutional Capsule Network for Traffic-Sign Recognition Using Mobile LiDAR Data With Digital Images

  2020cites this paper
• Ground Surface Recognition at Voxel Scale From Mobile Laser Scanning Data in Urban Environment

  2020cites this paper
• A Fusion Approach to Detect Traffic Signs Using Registered Color Images and Noisy Airborne LiDAR Data

  2020influential citation
• HPGCNN: Hierarchical Parallel Group Convolutional Neural Networks for Point Clouds Processing

  2020cites this paper
• LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

  2020cites this paper
• PointFusionNet: Point feature fusion network for 3D point clouds analysis

  2020cites this paper
• Learning multiscale spatial context for three-dimensional point cloud semantic segmentation

  2020cites this paper
• Classification and modelling of urban environments from point clouds for physical accessibility diagnosis and pedestrian pathfinding

  2019cites this paper
• GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud

  2019cites this paper
• The Mixed Kernel Function SVM-Based Point Cloud Classification

  2019cites this paper
• Assessment of various parameters on 3D semantic object-based point cloud labelling on urban LiDAR dataset

  2019cites this paper
• 3D Object Classification using 3D Racah Moments Convolutional Neural Networks

  2019cites this paper
• Review of Vehicle Detection Systems in Advanced Driver Assistant Systems

  2019cites this paper
• Object identication in 3D urban environments

  2019cites this paper
• Geometric modeling of man-made objects at different level of details. (Modélisation géométrique à différent niveau de détails d'objets fabriqués par l'homme)

  2019cites this paper
• Pole-Like Street Furniture Segmentation and Classification in Mobile LiDAR Data by Integrating Multiple Shape-Descriptor Constraints

  2019influential citation
• Analysis of a Hazard Prediction Model by Means of Variable Importance

  2019cites this paper
• Image-based identification and GIS-integration of vehicle restraint systems and evaluation of safety effects

  2019cites this paper
• Automated traffic sign and light pole detection in mobile LiDAR scanning data

  2019influential citation
• Content-Sensitive Multilevel Point Cluster Construction for ALS Point Cloud Classification

  2019cites this paper
• Automatic scene understanding and object identification in point clouds

  2019cites this paper
• A Novel Octree-Based 3-D Fully Convolutional Neural Network for Point Cloud Classification in Road Environment

  2019cites this paper
• Toward utilizing multitemporal multispectral airborne laser scanning, Sentinel-2, and mobile laser scanning in map updating

  2019cites this paper
• Multiscale Supervised Classification of Point Clouds with Urban and Forest Applications

  2019cites this paper
• A Hybrid Two-Stage 3D Object Recognition from Orthogonal Projections

  2019cites this paper
• Automatic 3-D Reconstruction of Indoor Environment With Mobile Laser Scanning Point Clouds

  2019cites this paper
• Automated Visual Recognizability Evaluation of Traffic Sign Based on 3D LiDAR Point Clouds

  2019cites this paper
• Towards Automatic Segmentation and Recognition of Multiple Precast Concrete Elements in Outdoor Laser Scan Data

  2019cites this paper
• Multi-Scale Hierarchical CRF for Railway Electrification Asset Classification From Mobile Laser Scanning Data

  2019cites this paper
• POINTNET FOR THE AUTOMATIC CLASSIFICATION OF AERIAL POINT CLOUDS

  2019cites this paper
• EXTRACTION AND SHAPE RECONSTRUCTION OF GUARDRAILS USING MOBILE MAPPING DATA

  2019cites this paper
• Deep Learning Methods for 3D Aerial and Satellite Data

  2019cites this paper
• Power Line Extraction From Mobile LiDAR Point Clouds

  2019influential citation