Abstract
In this paper we present a new approach for labeling 3D point clouds. We use Conditional Random Fields (CRFs) as an objective function, with unary energy term assessing the consistency of points with labels, and pairwise energy term between points and its neighbors. We propose a new method to learn this function from a collection of trained labels using JointBoost classifier formalism. By using CRFs with different geometric and contextual features, we show that our method enables the combination of semantic relations and achieves higher accuracy. We validate and demonstrate the efficiency of our method on complex urban laser scans and compare it with several alternative approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rusu, R.B., Holzbach, B., Blodow, N., Beetz, M.: Fast Geometric Point Labeling using Conditional Random Fields. In: Proceedings of IROS, USA (2009)
Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: Efficient and robust 3d object recognition. In: Proceedings of CVPR, San Francisco, CA, USA (2010)
Schoenberg, J., Nathan, A., Campbell, M.: Segmentation of dense range information in complex urban scenes. In: Proc. of IROS, Taipei (2010)
Munoz, D., Bagnell, J., Vandapel, N., Hebert, M.: Contextual classification with functional Max-Margin Markov Networks. In: Proc. of CVPR, USA (2009)
Anguelov, D., Taskar, B., Chatalbashev, V., Koller, D., Gupta, D., Heitz, G., Andrew, Y.: Discriminative Learning of Markov Random Fields for Segmentation of 3D Range Data. In: Proc. of CVPR, USA (2005)
Rusu, R.B., Blodow, N., Beetz, M.: Fast Point Feature Histograms (FPFH) for 3D Registration. In: Proceedings of ICRA (2009)
Shapovalov, R., Velizhev, A.: Cutting-Plane Training of Non-associative Markov Network for 3D Point Cloud Segmentation. In: International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (2011)
Golovinskiy, A., Funkhouser, T.: Min-cut based segmentation of point clouds. In: IEEE Workshop on Search in 3D and Video at ICCV (2009)
Nguyen, A., Le, B.: 3D Point Cloud Segmentation: A survey. In: Proceedings IEEE International Conference on Robotics, Automation and Mechatronics (RAM), Philippines (2013)
Rusu, R.B., Cousins, S.: 3D is here: Point Cloud Library (PCL). In: Proceedings of ICRA, China (2011)
Munoz, D., Vandapel, N., Hebert, M.: Onboard contextual classification of 3D point clouds with learned high-order Markov Random Fields. In: Proceedings of ICRA (2009)
Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3D Mesh Segmentation and Labeling. In: Proceedings of SIGGRAPH (2010)
Koppula, H.S., Anand, A., Joachims, T., Saxena, A.: Semantic Labeling of 3D Point Clouds for Indoor Scenes. In: Proceedings of NIPS (2011)
Huang, Q., Han, M., Wu, B., Ioffe, S.: A hierarchical conditional random field model for labeling and segmenting images of street scenes. In: Proceedings of CVPR (2011)
Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing Visual Features for Multiclass and Multiview Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. (2007)
Lim, E.H., Suter, D.: Conditional Random Field for 3D Point Clouds with Adaptive Data Reduction. In: International Conference on Cyberworlds (2007)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. Int. J. Comput. Vision 81(1)
Xiong, X., Munoz, D., Bagnell, J.A., Hebert, M.: 3D scene analysis via sequenced predictions over points and regions. In: Proceedings of ICRA (2011)
Johnson, A.E., Hebert, M.: Surface matching for object recognition in complex three-dimensional scenes. Image Vision Comput. 16 (1998)
Munoz, D., Vandapel, N., Hebert, M.: Directional associative markov network for 3D point cloud classification. In: Proceedings of 3DPVT, Atlanta, GA (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Nguyen, A., Le, B. (2014). Contextual Labeling 3D Point Clouds with Conditional Random Fields. In: Nguyen, N.T., Attachoo, B., Trawiński, B., Somboonviwat, K. (eds) Intelligent Information and Database Systems. ACIIDS 2014. Lecture Notes in Computer Science(), vol 8397. Springer, Cham. https://doi.org/10.1007/978-3-319-05476-6_59
Download citation
DOI: https://doi.org/10.1007/978-3-319-05476-6_59
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05475-9
Online ISBN: 978-3-319-05476-6
eBook Packages: Computer ScienceComputer Science (R0)