Investigation on Roof Segmentation for 3D Building Reconstruction from Aerial LIDAR Point Clouds

Three-dimensional (3D) reconstruction techniques are increasingly used to obtain 3D representations of buildings due to the broad range of applications for 3D city models related to sustainability, efficiency and resilience (i.e., energy demand estimation, estimation of the propagation of noise in an urban environment, routing and accessibility, flood or seismic damage assessment). With advancements in airborne laser scanning (ALS), 3D modeling of urban topography has increased its potential to automatize extraction of the characteristics of individual buildings. In 3D building modeling from light detection and ranging (LIDAR) point clouds, one major challenging issue is how to efficiently and accurately segment building regions and extract rooftop features. This study aims to present an investigation and critical comparison of two different fully automatic roof segmentation approaches for 3D building reconstruction. In particular, the paper presents and compares a cluster-based roof segmentation approach that uses (a) a fuzzy c-means clustering method refined through a density clustering and connectivity analysis, and (b) a region growing segmentation approach combined with random sample consensus (RANSAC) method. In addition, a robust 2.5D dual contouring method is utilized to deliver watertight 3D building modeling from the results of each proposed segmentation approach. The benchmark LIDAR point clouds and related reference data (generated by stereo plotting) of 58 buildings over downtown Toronto (Canada), made available to the scientific community by the International Society for Photogrammetry and Remote Sensing (ISPRS), have been used to evaluate the quality of the two proposed segmentation approaches by analysing the geometrical accuracy of the roof polygons. Moreover, the results of both approaches have been evaluated under different operating conditions against the real measurements (based on archive documentation and celerimetric surveys realized by a total station system) of a complex building located in the historical center of Matera (UNESCO world heritage site in southern Italy) that has been manually reconstructed in 3D via traditional Building Information Modeling (BIM) technique. The results demonstrate that both methods reach good performance metrics in terms of geometry accuracy. However, approach (b), based on region growing segmentation, exhibited slightly better performance but required greater computational time than the clustering-based approach.

[1]  Charles M. Eastman,et al.  BIM Handbook: A Guide to Building Information Modeling for Owners, Managers, Designers, Engineers and Contractors , 2008 .

[2]  Jie Shan,et al.  Building Extraction from LiDAR Point Clouds Based on Clustering Techniques , 2008 .

[3]  Norbert Pfeifer,et al.  New Associate Editor pp iii-iv Segmentation of airborne laser scanning data using a slope adaptive neighborhood , 2006 .

[4]  Constantine E. Kontokosta,et al.  Large-scale parameterization of 3D building morphology in complex urban landscapes using aerial LiDAR and city administrative data , 2019, Comput. Environ. Urban Syst..

[5]  Jan Dirk Wegner,et al.  Theme section “Urban object detection and 3D building reconstruction” , 2014 .

[6]  Robert Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[7]  Filip Biljecki,et al.  Applications of 3D City Models: State of the Art Review , 2015, ISPRS Int. J. Geo Inf..

[8]  Behnaz Bigdeli,et al.  3D reconstruction of buildings from LiDAR data considering various types of roof structures , 2017 .

[9]  Claus Brenner,et al.  Extraction of buildings and trees in urban environments , 1999 .

[10]  Dong Chen,et al.  LiDAR Point Clouds to 3-D Urban Models$:$ A Review , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Mani Golparvar-Fard,et al.  Segmentation of building point cloud models including detailed architectural/structural features and MEP systems , 2015 .

[12]  Uwe Soergel,et al.  Relevance assessment of full-waveform lidar data for urban area classification , 2011 .

[13]  G. Vosselman,et al.  3D RECONSTRUCTION OF BUILDING MODELS , 2000 .

[14]  Ulrich Neumann,et al.  2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds , 2010, ECCV.

[15]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[16]  Jaewook Jung,et al.  Implicit Regularization for Reconstructing 3D Building Rooftop Models Using Airborne LiDAR Data , 2017, Sensors.

[17]  Shaohui Sun,et al.  Aerial 3D Building Detection and Modeling From Airborne LiDAR Point Clouds , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Armin B. Cremers,et al.  Extracting Buildings from Aerial Images Using Hierarchical Aggregation in 2D and 3D , 1998, Comput. Vis. Image Underst..

[19]  Zhiliang Ma,et al.  A review of 3D reconstruction techniques in civil engineering and their applications , 2018, Adv. Eng. Informatics.

[20]  Zongze Zhao,et al.  Roof plane extraction from airborne lidar point clouds , 2017 .

[21]  Jie Shan,et al.  Segmentation and Reconstruction of Polyhedral Building Roofs From Aerial Lidar Point Clouds , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Yanming Chen,et al.  Three-Dimensional Reconstruction of Large Multilayer Interchange Bridge Using Airborne LiDAR Data , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[23]  Ayman Habib,et al.  INTERPOLATION OF LIDAR DATA AND AUTOMATIC BUILDING EXTRACTION , 2002 .

[24]  Ruisheng Wang,et al.  3D building modeling using images and LiDAR: a review , 2013 .

[25]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[26]  Jaewook Jung,et al.  Results of the ISPRS benchmark on urban object detection and 3D building reconstruction , 2014 .

[27]  T. Rabbani,et al.  SEGMENTATION OF POINT CLOUDS USING SMOOTHNESS CONSTRAINT , 2006 .

[28]  Stephen L. Chiu,et al.  Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..

[29]  Marco Zuliani,et al.  RANSAC for Dummies With examples using the RANSAC toolbox for Matlab™ & Octave and more... , 2014 .