Abstract
Several feature detectors for 3D point data have been proposed in the literature. They have been applied to various problems in computer vision and robotics. We use them to solve two fundamental problems in real-time robotics, namely the registration of laser scans as well as the detection of loops and places. We extend and modify existing feature detectors, combine them in a smart way and create a system, that solves these problems efficiently and better that existing other solutions.
We evaluate our system with data sets provided by other groups as well as our own data and we compare our results to those obtained with other algorithms.
Similar content being viewed by others
References
Proc. 3rd Int. Conf. on 3D Digital Imaging and Modeling (3DIM 2001) (IEEE Computer Soc., Quebec City, 2001).
L. A. Alexandre, “3D descriptors for object and category recognition: a comparative evaluation,” in Proc. Workshop on ColorDepth Camera Fusion in Robotics at the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) (Vilamoura, 2012).
M. Cummins and P. Newman, “Fabmap: Probabilistic localization and mapping in the space of appearance,” Int. J. Robotics Res. 27 (6), 647–665 (2008).
A. Frome, D. Huber, R. Kolluri, T. Bülow, and J. Malik, “Recognizing objects in range data sing regional point descriptors,” in Proc. Europ. Conf. on Computer Vision (ECCV), Lecture Notes in Computer Science, Ed. by T. Pajdla and J. Matas (Springer, Berlin, Heidelberg, 2004), Vol. 3023, pp. 224–237.
G. Grisetti, R. Kümmerle, C. Stachniss, U. Frese, and C. Hertzberg, “Hierarchical optimization on manifolds for online 2D and 3D mapping,” in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA) (Anchorage, AK, 2010).
C. Harris and M. Stephens, “A combined corner and edge detector,” in Proc. 4th Alvey Vision Conf. (Manchester, 1988), pp. 147–151.
S. Holzer, J. Shotton, and P. Kohli, “Learning to efficiently detect repeatable interest points in depth data,” in Proc. 12th European Conf. on Computer Vision (ECCV’12) (SpringerVerlag, Berlin, Heidelberg, 2012), pp. 200–213.
S. Izadi, D. Kim, O. Hilliges, D. Molyneaux, R. Newcombe, P. Kohli, J. Shotton, S. Hodges, D. Freeman, A. Davison, et al., “Kinectfusion: Realtime 3D reconstruction and interaction using a moving depth camera,” in Proc. 24th Annu. ACM Symp. on User Interface Software and Technology (Santa Barbara, 2011), pp. 559–568.
R. Kümmerle, G. Grisetti, H. Strasdat, K. Konolige, and W. Burgard, “G2O: A general framework for graph optimization,” in Proc. Int. Conf. on Robotics and Automation (ICRA) (Shanghai, 2011), pp. 3607–3613.
R. Kümmerle, B. Steder, C. Dornhege, M. Ruhnke, G. Grisetti, C. Stachniss, and A. Kleiner, “On measuring the accuracy of slam algorithms,” Autonom. Robots 27 (6), 387–407 (2009)
X. Li and I. Guskov, “Multiscale features for approximate alignment of pointbased surfaces,” in EG Symposium on Geometry Processing, Ed. by M. Desbrun and H. Pottmann (Eurographics Assoc., Vienna, 2005), pp. 217–226.
E. Olson, “Realtime correlative scan matching,” in Proc. IEEE Int. Conf. on Robotics and Automation (Kobe, 2009), pp. 4387–4393.
E. Olson and P. Agarwal, “Inference on networks of mixtures for robust robot mapping,” in Proc. Conf. on Robotics: Science and Systems (RSS) (Sydney, 2012).
E. Olson and Y. Li, “IPJC: The incremental posterior joint compatibility test for fast feature cloud matching,” in Proc. IEEE Int. Conf. on Intelligent Robots and Systems (IROS) (Vilamoura-Algarve, 2012).
M. Ruhnke, R. Kümmerle, G. Grisetti, and W. Burgard, “Highly accurate 3D surface models by sparse surface adjustment,” in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA) (St. Paul, MN, 2012), pp. 751–757.
S. Rusinkiewicz and M. Levoy, “Efficient variants of the ICP algorithm,” in Proc. Int. Conf. on 3D Digital Imaging and Modeling (Quebec City, 2001), pp. 145–152.
R. B. Rusu, N. Blodow, and M. Beetz, “Fast point feature histograms (FPFH) for 3D registration,” in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA) (Kobe, 2009), pp. 3212–3217.
R. B. Rusu, N. Blodow, Z. C. Marton, and M. Beetz, “Aligning point cloud views using persistent feature histograms,” in Proc. IEEE Int. Conf. on Intelligent Robots and Systems (IROS) (Nice, 2008), pp. 3384–3391.
R. B. Rusu, G. Bradski, R. Thibaux, and J. Hsu, “Fast 3D recognition and pose using the viewpoint feature histogram,” in Proc. Int. Conf. on Intelligent Robots and Systems (IROS) (Taipei, 2010), pp. 2155–2162.
R. B. Rusu and S. Cousins, “3D is here: Point cloud library (PCL),” in Proc. 2011 IEEE Int. Conf. on Robotics and Automation (ICRA) (Shanghai, 2011), pp. 1–4.
I. Sipiran and B. Bustos, “Harris 3D: A robust extension of the Harris operator for interest point detection on 3D meshes,” Visual Comput. 27 (11), 963–976 (2011).
B. Steder, G. Grisetti, and W. Burgard, “Robust place recognition for 3D range data based on point features,” in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA) (Anchorage, AK, 2010), pp. 1400–1405.
B. Steder, M. Ruhnke, S. Grzonka, and W. Burgard, “Place recognition in 3D scans using a combination of bag of words and point feature based relative pose estimation,” in Proc. Int. Conf. on Intelligent Robots and Systems (IROS) (San Francisco, 2011).
B. Steder, R. B. Rusu, K. Konolige, and W. Burgard, “Narf: 3D range image features for object recognition,” in Workshop on Defining and Solving Realistic Perception Problems in Personal Robotics at the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) (Taipei, 2010).
B. Steder, R. B. Rusu, K. Konolige, and W. Burgard, “Point feature extraction on 3D range scans taking into account object boundaries,” in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA) (Shanghai, 2011), pp. 2601–2608.
J. Stückler and S. Behnke, “Interest point detection in depth images through scalespace surface analysis,” in Proc. Int. Conf. on Robotics and Automation (ICRA) (Shanghai, 2011), pp. 3568–3574.
F. Tombari and L. Di Stefano, “Object recognition in 3D scenes with occlusions and clutter by hough voting,” in Proc. 4th Pacificim Symposium on Image and Video Technology (PSIVT) (Singapore, 2010), pp. 349–355.
F. Tombari, S. Salti, and L. Di Stefano, “Unique shape context for 3D data description,” in Proc. of the ACM Workshop on 3D Object Retrieval (3DOR) (New York, 2010), pp. 57–62.
F. Tombari, S. Salti, and L. Di Stefano, “Unique signatures of histograms for local surface description,” in Proc. Europ. Conf. on Computer Vision (ECCV’10) (Springer-Verlag, Berlin, Heidelberg, 2010), pp. 356–369.
F. Tombari, S. Salti, and L. Di Stefano, “A combined textureshape descriptor for enhanced 3D feature matching,” in Proc. IEEE Int. Conf. on Image Processing (ICIP) (Brussels, 2011), pp. 809–812.
A. Zaharescu, E. Boyer, K. Varanasi, and R. Horaud, “Surface feature detection and description with applications to mesh matching,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (Miami Beach, Florida, 2009), pp. 373–380.
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper uses the materials of the report submitted at the 11th International Conference “Pattern Recognition and Image Analysis: New Information Technologies,” Samara, Russia, September 23–28, 2013.
The article is published in the original.
Dietrich Paulus, born 1959, obtained a Bachelor degree in Computer Science from University of Western Ontario, London, Canada, followed by a diploma (Dipl.-Inf.) in Computer Science and a PhD (Dr.-Ing.) from Friedrich–Alexander University Erlangen-Nuremberg, Germany. He obtained his habilitation in Erlangen in 2001. Since 2001 he is at the Institute for Computational Visualistics at the University Koblenz–Landau, Germany where he became a full professor in 2002. His primary interests are computer vision and robot vision.
Andreas Mützel received a Bachelors degree in Computational Visualistics from the University of Koblenz–Landau, and graduated with a Masters Degree with honors in the same subject in 2013. He worked in the active vision group as a student assistant. His research interests were 3D mapping, especially in combination with 3D features. Since his graduation, he works with RV Realtime Visions GmbH, Koblenz.
Frank Neuhaus received a Diploma degree in Computer Science from the University of Koblenz–Landau where he graduated with honors in 2011. Since then he works as a research associate in the active vision group. His research is focused on 3D mapping and probabilistic modeling.
Rights and permissions
About this article
Cite this article
Mützel, A., Neuhaus, F. & Paulus, D. Geometric features for robust registration of point clouds. Pattern Recognit. Image Anal. 25, 174–186 (2015). https://doi.org/10.1134/S1054661815020182
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661815020182