Object Detection in Terrestrial Laser Scanning Point Clouds Based on Hough Forest

This letter presents a novel rotation-invariant method for object detection from terrestrial 3-D laser scanning point clouds acquired in complex urban environments. We utilize the Implicit Shape Model to describe object categories, and extend the Hough Forest framework for object detection in 3-D point clouds. A 3-D local patch is described by structure and reflectance features and then mapped to the probabilistic vote about the possible location of the object center. Objects are detected at the peak points in the 3-D Hough voting space. To deal with the arbitrary azimuths of objects in real world, circular voting strategy is introduced by rotating the offset vector. To deal with the interference of adjacent objects, distance weighted voting is proposed. Large-scale real-world point cloud data collected by terrestrial mobile laser scanning systems are used to evaluate the performance. Experimental results demonstrate that the proposed method outperforms the state-of-the-art 3-D object detection methods.

[1]  Thomas A. Funkhouser,et al.  Min-cut based segmentation of point clouds , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[2]  Luc Van Gool,et al.  Scene Cut: Class-Specific Object Detection and Segmentation in 3D Scenes , 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission.

[3]  Juha Hyyppä,et al.  Detection of Vertical Pole-Like Objects in a Road Environment Using Vehicle-Based Laser Scanning Data , 2010, Remote. Sens..

[4]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[5]  Hong Huo,et al.  Rotation-Invariant Object Detection of Remotely Sensed Images Based on Texton Forest and Hough Voting , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Bisheng Yang,et al.  Automated Extraction of Building Outlines From Airborne Laser Scanning Point Clouds , 2013, IEEE Geoscience and Remote Sensing Letters.

[7]  Konrad Schindler,et al.  IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS , 2012, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[8]  Bisheng Yang,et al.  A shape-based segmentation method for mobile laser scanning point clouds , 2013 .

[9]  Kostas Daniilidis,et al.  Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors , 2008, ECCV.

[10]  Claus Brenner,et al.  Extraction of Features from Mobile Laser Scanning Data for Future Driver Assistance Systems , 2009, AGILE Conf..

[11]  Vladimir G. Kim,et al.  Shape-based recognition of 3D point clouds in urban environments , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  Bruno Vallet,et al.  TREES DETECTION FROM LASER POINT CLOUDS ACQUIRED IN DENSE URBAN AREAS BY A MOBILE MAPPING SYSTEM , 2012 .

[13]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[14]  Javaid Iqbal,et al.  On the Improvement of Multi-Legged Locomotion over Difficult Terrains Using a Balance Stabilization Method: , 2012 .

[15]  Martial Hebert,et al.  Contextual classification with functional Max-Margin Markov Networks , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Bisheng Yang,et al.  Semiautomated Building Facade Footprint Extraction From Mobile LiDAR Point Clouds , 2013, IEEE Geoscience and Remote Sensing Letters.

[17]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Sidan Du,et al.  Super-Segments Based Classification of 3D Urban Street Scenes , 2012 .