Integrated Change Detection and Classification in Urban Areas Based on Airborne Laser Scanning Point Clouds

This paper suggests a new approach for change detection (CD) in 3D point clouds. It combines classification and CD in one step using machine learning. The point cloud data of both epochs are merged for computing features of four types: features describing the point distribution, a feature relating to relative terrain elevation, features specific for the multi-target capability of laser scanning, and features combining the point clouds of both epochs to identify the change. All these features are merged in the points and then training samples are acquired to create the model for supervised classification, which is then applied to the whole study area. The final results reach an overall accuracy of over 90% for both epochs of eight classes: lost tree, new tree, lost building, new building, changed ground, unchanged building, unchanged tree, and unchanged ground.

• Publication year

  2018

• Venue

  Italian National Conference on Sensors

• Publication date

  2018-02-01

• Fields of study

  Medicine, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.3390/s18020448PMID 29401656PMCID 5855963
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• The reported model reaches overall accuracy above 90% while distinguishing eight output classes for lost, new, changed, and unchanged trees, buildings, and ground.

  Confidence 0.97

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• Four feature groups are combined at the point level before training and prediction: point distribution, relative terrain elevation, multi-target capability, and cross-epoch change cues.

  Confidence 0.93

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• Change detection and class labeling are performed in one supervised machine-learning step on merged point clouds from both epochs.

  Confidence 0.95

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review

• 3d point clouds

  data

  Spatial point-based representations from the two acquisition epochs that serve as the input data for change analysis.

  Aliases: point clouds

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• airborne laser scanning

  sensor, acquisition method

  The remote-sensing acquisition method that produces the point-cloud observations used in the workflow.

  Aliases: ALS

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• eight output classes

  label set, classification target

  The final label set containing lost tree, new tree, lost building, new building, changed ground, unchanged building, unchanged tree, and unchanged ground.

  Aliases: eight classes

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• feature groups

  feature set, method

  The four categories of input features derived from point distribution, relative terrain elevation, multi-target capability, and both epochs together.

  Aliases: four feature types

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• overall accuracy

  evaluation metric

  The evaluation metric used to summarize how correctly the classifier assigns the final labels.

  Aliases: OA

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• point-level feature fusion

  method

  The combination of multiple feature groups at each point before model training and application.

  Aliases: pointwise feature fusion

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review
• supervised classification

  machine learning method

  A machine-learning setup trained from labeled samples to assign class labels to points.

  Aliases: machine-learning classification

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewAnonymous (n259mg7uxy) reviewAK (4715169a40) review

• Joint Discriminative Dictionary and Classifier Learning for ALS Point Cloud Classification

  2018cited by this paper
• Generating 3D city models without elevation data

  2017cited by this paper
• Classification of ALS Point Cloud with Improved Point Cloud Segmentation and Random Forests

  2017cited by this paper
• Global bare ground gain from 2000 to 2012 using Landsat imagery

  2017cited by this paper
• A structured regularization framework for spatially smoothing semantic labelings of 3D point clouds

  2017cited by this paper
• Object-based analysis of multispectral airborne laser scanner data for land cover classification and map updating

  2017cited by this paper
• LiDAR Data Filtering and DTM Generation

  2017cited by this paper
• Response of evapotranspiration to changes in land use and land cover and climate in China during 2001-2013.

  2017cited by this paper
• Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points

  2017cited by this paper
• Combining airborne laser scanning and Landsat data for statistical modeling of soil carbon and tree biomass in Tanzanian Miombo woodlands

  2017cited by this paper
• Building Classification from Lidar Data for Spatio-temporal Assessment of 3D Urban Developments

  2017cited by this paper
• 3D-Video-Based Computerized Behavioral Analysis for In Vivo Neuropharmacology and Neurophysiology in Rodents

  2017cited by this paper
• MULTISPECTRAL AIRBORNE LASER SCANNING FOR AUTOMATED MAP UPDATING

  2016cited by this paper
• 3D change detection – Approaches and applications

  2016cited by this paper
• Object Classification and Recognition From Mobile Laser Scanning Point Clouds in a Road Environment

  2016cited by this paper
• Discriminative-Dictionary-Learning-Based Multilevel Point-Cluster Features for ALS Point-Cloud Classification

  2016cited by this paper
• Automated Progress Monitoring Using Unordered Daily Construction Photographs and IFC-Based Building Information Models

  2015cited by this paper
• Assessment of Wooded Area Reduction by Airborne Laser Scanning

  2015cited by this paper
• Using Octrees to Detect Changes to Buildings and Trees in the Urban Environment from Airborne LiDAR Data

  2015influential reference
• A multilevel change detection method for buildings using laser scanning data and GIS data

  2015cited by this paper
• Effective Generation and Update of a Building Map Database Through Automatic Building Change Detection from LiDAR Point Cloud Data

  2015cited by this paper
• Simultaneous registration and change detection in multitemporal, very high resolution remote sensing data

  2015cited by this paper
• A Novel MKL Model of Integrating LiDAR Data and MSI for Urban Area Classification

  2015cited by this paper
• Detecting earthquake damage in urban area: application to COSMO-SkyMed imagery of L’Aquila earthquake

  2015cited by this paper
• A Correspondence Framework for ALS Strip Adjustments based on Variants of the ICP Algorithm

  2015cited by this paper
• Change detection from differential airborne LiDAR using a weighted anisotropic iterative closest point algorithm

  2014cited by this paper
• Contextual classification of lidar data and building object detection in urban areas

  2014cited by this paper
• Object-Based Analysis of Airborne LiDAR Data for Building Change Detection

  2014cited by this paper
• OPALS - A framework for Airborne Laser Scanning data analysis

  2014influential reference
• Improving Change Detection in Forest Areas Based on Stereo Panchromatic Imagery Using Kernel MNF

  2014cited by this paper
• Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features

  2014cited by this paper
• Assessment of the image misregistration effects on object-based change detection

  2014cited by this paper
• Detecting tropical forest biomass dynamics from repeated airborne lidar measurements

  2013cited by this paper
• Damage assessment in urban areas using post-earthquake airborne PolSAR imagery

  2013cited by this paper
• Change detection of buildings from satellite imagery and lidar data

  2013cited by this paper
• Detection and Classification of Changes in Buildings from Airborne Laser Scanning Data

  2013cited by this paper
• Change detection in urban areas by object-based analysis and on-the-fly comparison of multi-view ALS data

  2013cited by this paper
• Feature relevance assessment for the semantic interpretation of 3D point cloud data

  2013cited by this paper
• Lidar-based change detection and change-type determination in urban areas

  2013cited by this paper
• Airborne photogrammetry and lidar for DSM extraction and 3D change detection over an urban area – a comparative study

  2013cited by this paper
• A Coarse Elevation Map-based Registration Method for Super-resolution of Three-line Scanner Images

  2013cited by this paper
• Determining sea surface heights using small footprint airborne laser scanning

  2013cited by this paper
• A 3D-Video-Based Computerized Analysis of Social and Sexual Interactions in Rats

  2013cited by this paper
• Change detection in deforestation using high resolution satellite image with Haar wavelet transforms

  2013cited by this paper
• IMPROVING 3D LIDAR POINT CLOUD REGISTRATION USING OPTIMAL NEIGHBORHOOD KNOWLEDGE

  2012cited by this paper
• Convolutional-Recursive Deep Learning for 3D Object Classification

  2012cited by this paper
• Use of LIDAR in landslide investigations: a review

  2012cited by this paper
• Urban vegetation detection using radiometrically calibrated small-footprint full-waveform airborne LiDAR data

  2012cited by this paper
• Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests

  2011cited by this paper
• Monitoring changes of 3D building elements from unordered photo collections

  2011cited by this paper
• Relevance assessment of full-waveform lidar data for urban area classification

  2011cited by this paper
• AUTOMATED UPDATING AND MAINTENANCE OF 3D CITY MODELS

  2010cited by this paper
• Change detection for earthquake damage assessment in built-up areas using very high resolution optical and SAR imagery

  2010cited by this paper
• Monitoring of collapsed built-up areas with high resolution SAR images

  2010cited by this paper
• Automatic Detection of Buildings and Changes in Buildings for Updating of Maps

  2010cited by this paper
• A FEATURE BASED APPROACH TO AUTOMATIC CHANGE DETECTION FROM LIDAR DATA IN URBAN AREAS

  2009cited by this paper
• Detection of building regions using airborne LiDAR : a new combination of raster and point cloud based GIS methods

  2009cited by this paper
• Point cloud segmentation towards urban ground modeling

  2009cited by this paper
• Forest transition in Vietnam and its environmental impacts

  2008cited by this paper
• Assessing changes of forest area and shrub encroachment in a mire ecosystem using digital surface models and CIR aerial images

  2008cited by this paper
• Object-Based Point Cloud Analysis of Full-Waveform Airborne Laser Scanning Data for Urban Vegetation Classification

  2008cited by this paper
• Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments

  2008cited by this paper
• Using landsat data to determine land use/land cover changes in Samsun, Turkey

  2007cited by this paper
• Land-cover change detection using multi-temporal MODIS NDVI data

  2006cited by this paper
• AUTOMATIC DETECTION OF CHANGES FROM LASER SCANNER AND AERIAL IMAGE DATA FOR UPDATING BUILDING MAPS

  2004cited by this paper
• Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data

  2004cited by this paper
• Change detection techniques

  2004cited by this paper
• Change detection for updating medium scale maps using laster altimetry

  2004cited by this paper
• LIDAR-based change detection of buildings in dense urban areas

  2004cited by this paper
• Argument free clustering for large spatial point-data sets via boundary extraction from Delaunay Diagram

  2002cited by this paper
• The experimental study on tree growth in XLPE using 3D PD patterns

  2000cited by this paper
• Change detection of buildings using an airborne laser scanner

  1999cited by this paper
• Support-Vector Networks

  1995cited by this paper
• Change detection for monitoring forest defoliation

  1994cited by this paper

• Synthetic learning for primitive-based building model reconstruction from point clouds

  2026cites this paper
• ME-CPT: Multitask Enhanced Cross-Temporal Point Transformer for Urban 3-D Change Detection

  2026cites this paper
• Automating maintenance of road Geometric Digital Twins through single scan instance aware point cloud change retrieval

  2025cites this paper
• Semantic and Geometric Fusion for Object-Based 3D Change Detection in LiDAR Point Clouds

  2025cites this paper
• Ms-DANet: Multiscale Difference-Aware Network for 3-D Point Cloud Change Detection

  2025cites this paper
• Object localization and change detection in urban environments using dashcam videos

  2025cites this paper
• Effectiveness of Unmanned Aerial Vehicle-Based LiDAR for Assessing the Impact of Catastrophic Windstorm Events on Timberland

  2025cites this paper
• An Edge-Enhanced Siamese Network for 3D Change Detection

  2025cites this paper
• Predicting Diffusion Coefficients in Nafion Membranes during the Soaking Process Using a Machine Learning Approach

  2024cites this paper
• Change Detection in Point Clouds Using 3D Fractal Dimension

  2024cites this paper
• 3D Change Detection Method for Exterior Wall of LNG Storage Tank Supported by Multi‐Source Spatial Data

  2024cites this paper
• Automatic building footprint extraction from photogrammetric and LiDAR point clouds using a novel improved-Octree approach

  2024cites this paper
• Three-dimensional Change Detection and Description in Complex Construction Scenarios

  2024cites this paper
• PGN3DCD: Prior-Knowledge-Guided Network for Urban 3-D Point Cloud Change Detection

  2024cites this paper
• A Hybrid Algorithm for Urban LULC Change Detection for Building Smart-city by Using WorldView Images

  2023cites this paper
• Détection de changements urbains 3D par un réseau Siamois sur nuage de points 3D Urban Change Detection With Point Cloud Siamese Network *

  2023influential citation
• RAFNet: Interdomain Representation Alignment and Fine-Tuning for Image Series Classification

  2023cites this paper
• DC3DCD: unsupervised learning for multiclass 3D point cloud change detection

  2023influential citation
• Deep unsupervised learning for 3D ALS point clouds change detection

  2023cites this paper
• PBFormer: Point and Bi-Spatiotemporal Transformer for Pointwise Change Detection of 3D Urban Point Clouds

  2023cites this paper
• Change Detection Needs Change Information: Improving Deep 3-D Point Cloud Change Detection

  2023cites this paper
• Object-based 3D building change detection using point-level change indicators

  2023cites this paper
• Semantic supported urban change detection using ALS point clouds

  2023cites this paper
• 3D urban object change detection from aerial and terrestrial point clouds: A review

  2023cites this paper
• Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data

  2023influential citation
• Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning

  2023cites this paper
• Change detection of urban objects using 3D point clouds: A review

  2023cites this paper
• RANSAC-based multi primitive building reconstruction from 3D point clouds

  2022cites this paper
• Three Dimensional Change Detection Using Point Clouds: A Review

  2022cites this paper
• DEFINING THE FUNCTIONAL SPACE OF BUS STOPS FROM MLS POINT CLOUDS

  2022cites this paper
• Bilevel Thresholding-Based Iterative Analysis for Building-Surface Damage Detection in a Postearthquake Environment

  2022cites this paper
• 3D point cloud data processing with machine learning for construction and infrastructure applications: A comprehensive review

  2022cites this paper
• BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK

  2022cites this paper
• Multi-Feature Airborne Lidar Strip Adjustment Method Combined with Tensor Voting Algorithm

  2021cites this paper
• The use of Otsu algorithm and multi-temporal airborne LiDAR data to detect building changes in urban space

  2021cites this paper
• A Multi-Feature Fusion Using Deep Transfer Learning for Earthquake Building Damage Detection

  2021cites this paper
• Building Change Detection of Airborne Laser Scanning and Dense Image Matching Point Clouds using Height and Class Information

  2021cites this paper
• Change Detection in Urban Point Clouds: An Experimental Comparison with Simulated 3D Datasets

  2021cites this paper
• CHANGE DETECTION OF TIME-SERIES 3D POINT CLOUDS USING ROBUST PRINCIPAL COMPONENT ANALYSIS

  2021cites this paper
• 3D URBAN CHANGE DETECTION WITH POINT CLOUD SIAMESE NETWORKS

  2021influential citation
• A CONCEPT FOR THE SEGMENTATION OF INDIVIDUAL URBAN TREES FROM DENSE MLS POINT CLOUDS

  2021cites this paper
• New semi-automatic 3D registration method for terrestrial laser scanning data of bridge structures based on artificial neural networks

  2021cites this paper
• Benchmarking Change Detection in Urban 3D Point Clouds

  2021cites this paper
• Change Detection of Urban Trees in MLS Point Clouds Using Occupancy Grids

  2021cites this paper
• Machine Learning-Based Structural Damage Identification Within Three-Dimensional Point Clouds

  2021cites this paper
• Voxel Change: Big Data–Based Change Detection for Aerial Urban LiDAR of Unequal Densities

  2021cites this paper
• Virtual Reconstruction System of Building Spatial Structure Based on Laser 3D Scanning under Multivariate Big Data Fusion

  2021cites this paper
• Building change detection from multitemporal airborne LiDAR data: assessment of different approaches

  2021influential citation
• EFFICIENT LARGE-SCALE AIRBORNE LIDAR DATA CLASSIFICATION VIA FULLY CONVOLUTIONAL NETWORK

  2020cites this paper
• Augmented Semantic Signatures of Airborne LiDAR Point Clouds for Comparison

  2020cites this paper
• FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning

  2020cites this paper
• An Object-Based Bidirectional Method for Integrated Building Extraction and Change Detection between Multimodal Point Clouds

  2020cites this paper
• Augmented Semantic Signatures of Airborne LiDAR Point Clouds for Determining Change in Time-varying Data

  2020cites this paper
• Generalized Sparse Convolutional Neural Networks for Semantic Segmentation of Point Clouds Derived from Tri-Stereo Satellite Imagery

  2020cites this paper
• Using extracted member properties for laser‐based surface damage detection and quantification

  2020cites this paper
• Uncertainty management for robust probabilistic change detection from multi-temporal Geoeye-1 imagery

  2020cites this paper
• COMPARISON OF SOFTWARE FOR AIRBORNE LASER SCANNING DATA PROCESSING IN SMART CITY APPLICATIONS

  2019cites this paper
• Combination of Post-Earthquake LiDAR Data and Satellite Imagery for Buildings Damage detection

  2019cites this paper
• Airborne lidar change detection: An overview of Earth sciences applications

  2019cites this paper
• A Precision Estimation Method for Volumetric Changes

  2019cites this paper
• CHANGE DETECTION BETWEEN DIGITAL SURFACE MODELS FROM AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING USING CONVOLUTIONAL NEURAL NETWORKS

  2019cites this paper
• Developing an Algorithm for Buildings Extraction and Determining Changes from Airborne LiDAR, and Comparing with R-CNN Method from Drone Images

  2019cites this paper
• Urban area change visualization and analysis using high density spatial data from time series aerial images

  2019cites this paper
• Comparative analysis of machine learning and point-based algorithms for detecting 3D changes in buildings over time using bi-temporal lidar data

  2019cites this paper
• FORSAT: a 3D forest monitoring system for cover mapping and volumetric 3D change detection

  2019cites this paper
• Improving LiDAR classification accuracy by contextual label smoothing in post-processing

  2019cites this paper
• CNN-based estimation of pre- and post-earthquake height models from single optical images for identification of collapsed buildings

  2019cites this paper
• Coarse-to-Fine Classification of Road Infrastructure Elements from Mobile Point Clouds Using Symmetric Ensemble Point Network and Euclidean Cluster Extraction

  2019cites this paper
• Strip Adjustment of Airborne LiDAR Data in Urban Scenes Using Planar Features by the Minimum Hausdorff Distance

  2019cites this paper
• Detecting Building Changes between Airborne Laser Scanning and Photogrammetric Data

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

  2019cites this paper
• Transfer Learning for Changes Detection in Optical Remote Sensing Imagery

  2019cites this paper
• Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information

  2019cites this paper
• An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection

  2018cites this paper
• Automatic Building Extraction from Image and LiDAR Data with Active Contour Segmentation

  2018cites this paper
• Change Detection between Multimodal Remote Sensing Data Using Siamese CNN

  2018cites this paper
• Unsupervised extraction of urban features from airborne lidar data by using self-organizing maps

  2018cites this paper
• URBAN AREA CHANGE DETECTION USING TIME SERIES AERIAL IMAGES

  2018cites this paper
• Beyond Siamese KPConv: Early Encoding and Less Supervision

  year unknowncites this paper