DETECTION OF BUILDING ROOFS AND FACADES FROM AERIAL LASER SCANNING DATA USING DEEP LEARNING

Abstract. In this work we test the power of prediction of deep learning for detection of buildings from aerial laser scanner point cloud information. Automatic extraction of built features from remote sensing data is of extreme interest for many applications. In particular latest paradigms of 3D mapping of buildings, such as CityGML and BIM, can benefit from an initial determination of building geometries. In this work we used a LiDAR dataset of urban environment from the ISPRS benchmark on urban object detection. The dataset is labelled with eight classes, two were used for this investigation: roof and facades. The objective is to test how TensorFlow neural network for deep learning can predict these two classes. Results show that for “roof” and “facades” semantic classes respectively, recall is 84% and 76% and precision is 72% and 63%. The number and distribution of correct points well represent the geometry, thus allowing to use them as support for CityGML and BIM modelling. Further tuning of the hidden layers of the DL model will likely improve results and will be tested in future investigations.

[1]  Maria Antonia Brovelli,et al.  LiDAR digital building models for true orthophoto generation , 2010 .

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

[3]  Andreas Donaubauer,et al.  3DCityDB - a 3D geodatabase solution for the management, analysis, and visualization of semantic 3D city models based on CityGML , 2018, Open Geospatial Data, Software and Standards.

[4]  Fabio Remondino,et al.  A REVIEW OFPOINT CLOUDS SEGMENTATION AND CLASSIFICATION ALGORITHMS , 2017 .

[5]  E. Rupnik,et al.  MicMac – a free, open-source solution for photogrammetry , 2017, Open Geospatial Data, Software and Standards.

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

[7]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[8]  Henrique Lorenzo,et al.  INDOOR NAVIGATION FROM POINT CLOUDS: 3D MODELLING AND OBSTACLE DETECTION , 2016 .

[9]  Yan Lu,et al.  Simplified markov random fields for efficient semantic labeling of 3D point clouds , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  J. Niemeyer,et al.  Contextual classification of lidar data and building object detection in urban areas , 2014 .

[11]  Michael Weinmann,et al.  A Classification-Segmentation Framework for the Detection of Individual Trees in Dense MMS Point Cloud Data Acquired in Urban Areas , 2017, Remote. Sens..

[12]  Martial Hebert,et al.  Contextual classification with functional Max-Margin Markov Networks , 2009, CVPR.

[13]  S. J. Oude Elberink,et al.  Multiple-entity based classification of airborne laser scanning data in urban areas , 2014 .

[14]  Chao Wang,et al.  Automatic BIM component extraction from point clouds of existing buildings for sustainability applications , 2015 .

[15]  Andrea Masiero,et al.  Implementation and assessment of two density-based outlier detection methods over large spatial point clouds , 2018, Open Geospatial Data, Software and Standards.

[16]  Konrad Schindler,et al.  FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY , 2016 .

[17]  Stefan Hinz,et al.  Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers , 2015 .

[18]  Fabio Remondino,et al.  3d Surveying and modelling of the Archaeological Area of Paestum, Italy , 2015 .

[19]  Luigi Barazzetti,et al.  A COMPARATIVE STUDY AMONG THREE REGISTRATION ALGORITHMS: PERFORMANCE, QUALITY ASSURANCE AND ACCURACY , 2019, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[20]  Florent Lafarge,et al.  Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation , 2012, International Journal of Computer Vision.

[21]  Jing Xiao,et al.  Fusion of airborne laserscanning point clouds and images for supervised and unsupervised scene classification , 2014 .

[22]  María Concepcion Alonso,et al.  Automatic Detection and Classification of Pole-Like Objects in Urban Point Cloud Data Using an Anomaly Detection Algorithm , 2015, Remote. Sens..

[23]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[24]  Antonio Adán,et al.  Autonomous Mobile Scanning Systems for the Digitization of Buildings: A Review , 2019, Remote. Sens..

[25]  Valentina Bonora,et al.  THE FLORENCE BAPTISTERY: 3-D SURVEY AS A KNOWLEDGE TOOL FOR HISTORICAL AND STRUCTURAL INVESTIGATIONS , 2016 .

[26]  R. Reulke,et al.  Remote Sensing and Spatial Information Sciences , 2005 .

[27]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[28]  David Suter,et al.  3D terrestrial LIDAR classifications with super-voxels and multi-scale Conditional Random Fields , 2009, Comput. Aided Des..

[29]  Antonio Costanzo,et al.  Combined Use of Terrestrial Laser Scanning and IR Thermography Applied to a Historical Building , 2014, Sensors.

[30]  Uwe Soergel,et al.  HIERARCHICAL HIGHER ORDER CRF FOR THE CLASSIFICATION OF AIRBORNE LIDAR POINT CLOUDS IN URBAN AREAS , 2016 .

[31]  Aleksey Boyko,et al.  Extracting roads from dense point clouds in large scale urban environment , 2011 .