Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas
Open Access
- 1 January 2018
- journal article
- research article
- Published by Taylor & Francis Ltd in European Journal of Remote Sensing
- Vol. 51 (1), 978-990
- https://doi.org/10.1080/22797254.2018.1522934
Abstract
Point clouds are a very detailed and accurate vector data model of 3D geographic information. In contrast to other data models, no standard has been defined for visualization and management of point clouds based on levels of detail (LOD). This paper proposes the application of the concept of LODs to point clouds and defines the LOD0 for point cloud classification (the lowest possible level of detail) as urban and non-urban. A methodology based on the use of machine learning techniques is developed to perform LOD0 classification to airborne LiDAR data. Point clouds acquired with airborne laser scanner (ALS) are structured in grid maps and geometric features related with Z distribution and roughness are extracted from each cell. Six machine learning classifiers have been trained with datasets including urban (cities) and non-urban samples (farmlands and forests). The influence of grid size, point density, number of features and classifier type are analysed in detail. The classifiers have been tested in three case studies. The best results correspond to a grid size of 100 m and the use of 12 geometric features. The accuracy is around 90% in all tests and Cohen’s Kappa index reaches 81% in the best of cases.Keywords
Funding Information
- Ministerio de Economía, Industria y Competitividad, Gobierno de España (RTC-2016-5257-7, TIN2016-77158-C4-2-R)
- Dirección General de Tráfico (SPIP2017-02122)
- Universidade de Vigo (00VI 131H 641.02)
- Xunta de Galicia (ED431C 2016-038, ED481B 2016/079-0)
This publication has 53 references indexed in Scilit:
- Urban accessibility diagnosis from mobile laser scanning dataISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Lidar-based change detection and change-type determination in urban areasInternational Journal of Remote Sensing, 2012
- Accuracy Assessment of Digital Surface Models Based on WorldView-2 and ADS80 Stereo Remote Sensing DataSensors, 2012
- Fusion of High Resolution Aerial Multispectral and LiDAR Data: Land Cover in the Context of Urban Mosquito HabitatRemote Sensing, 2011
- Evaluation of the self‐organizing map classifier for building detection from lidar data and multispectral aerial imagesJournal of Spatial Science, 2009
- Object-based land cover classification using airborne LiDARRemote Sensing of Environment, 2008
- Object‐based classification of residential land use within Accra, Ghana based on QuickBird satellite dataInternational Journal of Remote Sensing, 2007
- Joint analysis of SAR, LIDAR and aerial imagery for simultaneous extraction of land cover, DTM and 3D shape of buildingsInternational Journal of Remote Sensing, 2002
- A Generalization of Cohen's Kappa Agreement Measure to Interval Measurement and Multiple RatersEducational and Psychological Measurement, 1988
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960