Comparison of Different Feature Sets for TLS Point Cloud Classification

Point cloud classification is an essential requirement for effectively utilizing point cloud data acquired by Terrestrial laser scanning (TLS). Neighborhood selection, feature selection and extraction, and classification of points based on the respective features constitute the commonly used workflow of point cloud classification. Feature selection and extraction has been the focus of many studies, and the choice of different features has had a great impact on classification results. In previous studies, geometric features were widely used for TLS point cloud classification, and only a few studies investigated the potential of both intensity and color on classification using TLS point cloud. In this paper, the geometric features, color features, and intensity features were extracted based on a supervoxel neighborhood. In addition, the original intensity was also corrected for range effect, which is why the corrected intensity features were also extracted. The different combinations of these features were tested on four real-world data sets. Experimental results demonstrate that both color and intensity features can complement the geometric features to help improve the classification results. Furthermore, the combination of geometric features, color features, and corrected intensity features together achieves the highest accuracy in our test.

[1]  Bruno Vallet,et al.  STREAMED VERTICAL RECTANGLE DETECTION IN TERRESTRIAL LASER SCANS FOR FACADE DATABASE PRODUCTION , 2012 .

[2]  Lin Li,et al.  Recognition and Reconstruction of Zebra Crossings on Roads from Mobile Laser Scanning Data , 2016, ISPRS Int. J. Geo Inf..

[3]  Kiyun Yu,et al.  Assessing the Possibility of Landcover Classification Using Lidar Intensity Data , 2002 .

[4]  Bo Du,et al.  A Three-Step Approach for TLS Point Cloud Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[5]  C. E. Harris,et al.  Laser Radar Systems , 1991 .

[6]  Pankaj Kumar,et al.  Automated road markings extraction from mobile laser scanning data , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Kai Tan,et al.  Correction of Incidence Angle and Distance Effects on TLS Intensity Data Based on Reference Targets , 2016, Remote. Sens..

[8]  Rama Rao Nidamanuri,et al.  A supervoxel-based spectro-spatial approach for 3D urban point cloud labelling , 2016 .

[9]  N. Pfeifer,et al.  Correction of laser scanning intensity data: Data and model-driven approaches , 2007 .

[10]  Boris Jutzi,et al.  Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features , 2014 .

[11]  Kai Tan,et al.  Intensity data correction based on incidence angle and distance for terrestrial laser scanner , 2015 .

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

[13]  Fan Zhang,et al.  Intensity Correction of Terrestrial Laser Scanning Data by Estimating Laser Transmission Function , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Nicholas Wilson,et al.  A Review of LIDAR Radiometric Processing: From Ad Hoc Intensity Correction to Rigorous Radiometric Calibration , 2015, Sensors.

[15]  Anttoni Jaakkola,et al.  Analysis of Incidence Angle and Distance Effects on Terrestrial Laser Scanner Intensity: Search for Correction Methods , 2011, Remote. Sens..

[16]  Konrad Schindler,et al.  Joint classification and contour extraction of large 3D point clouds , 2017 .

[17]  Weiqi Zhou,et al.  An Object-Based Approach for Urban Land Cover Classification: Integrating LiDAR Height and Intensity Data , 2013, IEEE Geoscience and Remote Sensing Letters.

[18]  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..

[19]  Peng Li,et al.  3-D Point Cloud Object Detection Based on Supervoxel Neighborhood With Hough Forest Framework , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[21]  Michael Weinmann,et al.  A Hybrid Semantic Point Cloud Classification-Segmentation Framework Based on Geometric Features and Semantic Rules , 2017, PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science.

[22]  Q. Li,et al.  DAMAGE DETECTION FOR HISTORICAL ARCHITECTURES BASED ON TLS INTENSITY DATA , 2018 .

[23]  Florentin Wörgötter,et al.  Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Juntao Yang,et al.  A probabilistic graphical model for the classification of mobile LiDAR point clouds , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[25]  Cheng Wang,et al.  Toward better boundary preserved supervoxel segmentation for 3D point clouds , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

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

[27]  Anthony Mandow,et al.  Voxel-Based Neighborhood for Spatial Shape Pattern Classification of Lidar Point Clouds with Supervised Learning , 2017, Sensors.

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

[29]  Xiangguo Lin,et al.  SVM-Based Classification of Segmented Airborne LiDAR Point Clouds in Urban Areas , 2013, Remote. Sens..

[30]  Ahmad Kamal Aijazi,et al.  Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation , 2013, Remote. Sens..

[31]  Cheng Wang,et al.  Using mobile laser scanning data for automated extraction of road markings , 2014 .

[32]  C. Mallet,et al.  AIRBORNE LIDAR FEATURE SELECTION FOR URBAN CLASSIFICATION USING RANDOM FORESTS , 2009 .