Volume I-3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-3, 179-184, 2012
https://doi.org/10.5194/isprsannals-I-3-179-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-3, 179-184, 2012
https://doi.org/10.5194/isprsannals-I-3-179-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.

  20 Jul 2012

20 Jul 2012

IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS

A. Velizhev1,2, R. Shapovalov1, and K. Schindler3 A. Velizhev et al.
  • 1Graphics & Media Lab, Lomonosov Moscow State University, Russia
  • 2Photogrammetry Lab, Moscow State University of Geodesy and Cartography, Russia
  • 3Photogrammetry and Remote Sensing Group, ETH Zürich, Switzerland

Keywords: Recognition, LiDAR, Laser Scanning, Point Cloud

Abstract. We present a method for automatic object localization and recognition in 3D point clouds representing outdoor urban scenes. The method is based on the implicit shape models (ISM) framework, which recognizes objects by voting for their center locations. It requires only few training examples per class, which is an important property for practical use. We also introduce and evaluate an improved version of the spin image descriptor, more robust to point density variation and uncertainty in normal direction estimation. Our experiments reveal a significant impact of these modifications on the recognition performance. We compare our results against the state-of-the-art method and get significant improvement in both precision and recall on the Ohio dataset, consisting of combined aerial and terrestrial LiDAR scans of 150,000 m2 of urban area in total.