Abstract
This paper addresses classification of 3D point cloud data from natural environments based on voxels. The proposed model uses multi-layer perceptrons to classify voxels based on a statistic geometric analysis of the spatial distribution of inner points. Geometric features such as tubular structures or flat surfaces are identified regardless of their orientation, which is useful for unstructured or natural environments. Furthermore, the combination of voxels and neural networks pursues faster computation than alternative strategies. The model has been successfully tested with 3D laser scans from natural environments.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Cole, D., Newman, P.: Using laser range data for 3D SLAM in outdoor environments. Proceedings - IEEE International Conference on Robotics and Automation. 2006, 1556–1563 (2006)
Rusu, R., Sundaresan, A., Morisset, B., Hauser, K., Agrawal, M., Jean-Claude, L., Beetz, M.: Leaving flatland: Efficient real-time three-dimensional perception and motion planning. Journal of Field Robotics 26(10), 841–862 (2009)
Mandow, A., Martínez, J., Reina, A., Morales, J.: Fast range-independent spherical subsampling of 3D laser scanner points and data reduction performance evaluation for scene registration. Pattern Recognition Letters 31(11), 1239–1250 (2010)
Linhui, L., Mingheng, Z., Lie, G., Yibing, Z.: Stereo vision based obstacle avoidance path-planning for cross-country intelligent vehicle. In: 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009, vol. 5, pp. 463–467 (2009)
Zhu, X., Zhao, H., Liu, Y., Zhao, Y., Zha, H.: Segmentation and classification of range image from an intelligent vehicle in urban environment. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1457–1462 (2010)
Othmani, A., Piboule, A., Dalmau, O., Lomenie, N., Mokrani, S., Voon, L.F.C.L.Y.: Tree species classification based on 3D bark texture analysis. In: Klette, R., Rivera, M., Satoh, S. (eds.) PSIVT 2013. LNCS, vol. 8333, pp. 279–289. Springer, Heidelberg (2014)
Douillard, B., Brooks, A., Ramos, F.: A 3D laser and vision based classifier. In: 2009 5th International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), pp. 295–300 (2009)
Yu, Y., Li, J., Guan, H., Wang, C., Yu, J.: Semiautomated extraction of street light poles from mobile LIDAR point-clouds. IEEE Transactions on Geoscience and Remote Sensing 53(3), 1374–1386 (2015)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)
Sima, M.C., Nüchter, A.: An extension of the Felzenszwalb-Huttenlocher segmentation to 3D point clouds. In: Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 8783, pp. 878302–878306 (2013)
Hao, W., Wang, Y.: Classification-based scene modeling for urban point clouds. Optical Engineering 53(3), 033110 (2014)
Zhou, Y., Yu, Y., Lu, G., Du, S.: Super-segments based classification of 3D urban street scenes. International Journal of Advanced Robotic Systems 9(248), 1–8 (2012)
Lalonde, J., Vandapel, N., Huber, D., Hebert, M.: Natural terrain classification using three-dimensional ladar data for ground robot mobility. Journal of Field Robotics 23(10), 839–861 (2006)
Borcs, A., Jozsa, O., Benedek, C.: Object extraction in urban environments from large-scale dynamic point cloud datasets. In: Proceedings - International Workshop on Content-Based Multimedia Indexing, pp. 191–194 (2013)
Seo, B., Chung, M.: Traversable ground detection based on geometric-featured voxel map. In: FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, pp. 31–35 (2013)
Choe, Y., Shim, I., Chung, M.: Geometric-featured voxel maps for 3D mapping in urban environments. In: 9th IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2011, pp. 110–115 (2011)
Habermann, D., Hata, A., Wolf, D., Osorio, F.: Artificial neural nets object recognition for 3D point clouds. In: 2013 Brazilian Conference on Intelligent Systems (BRACIS), pp. 101–106 (2013)
Reina, A., Martínez, J., Mandow, A., Morales, J., García-Cerezo, A.: Collapsible cubes: Removing overhangs from 3D point clouds to build local navigable elevation maps. In: IEEE Conference on Advanced Intelligence Mecatronics (AIM), pp. 1012–1017 (2014)
Medioni, G., Lee, M., Tang, C.: A computational framework for segmentation and grouping. Elsevier Science Inc., New York (2000)
Bilmes, J.: A gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Tech. Rep. ICSI-TR-97-021. The International Computer Science Institute, University of Berkeley, Berkeley (1997)
Duda, R., Hart, P., Stork, D.: Pattern classification. Wiley Interscience (2000)
Funahashi, K.: Multilayer neural networks and Bayes decision theory. Neural Networks 11(2), 209–213 (1998)
Patterson, D.W.: Artificial neural networks, theory and applications. Prentice-Hall Series in Advanced Communications, Prentice Hall (1996)
Amari, S., Murata, N., Muller, K.R., Finke, M., Yang, H.: Statistical theory of overtraining - is cross-validation asymptotically effective? Adv Neural Inform Process Syst. 8, 176–182 (1996)
Janssen, P., Stoica, P., Söderström, T., Eykhoff, P.: Model structure selection for multivariable systems by cross-validation. International Journal of Control 47(6), 1737–1758 (1988)
Plaza-Leiva, V.: Local Semantic Map based on 3D data for navigability. Master’s thesis, Univeristy of Málaga, ETSII (2013)
Morales, J., Martinez, J., Mandow, A., Pequeno-Boter, A., Garcia-Cerezo, A.: Design and development of a fast and precise low-cost 3D laser rangefinder. In: 2011 IEEE International Conference on Mechatronics (ICM), pp. 621–626 (2011)
Elhabiby, M., Teskey, W.J.: Stop-and-go 3D laser scanning and mobile mapping. B. Sc. Thesis (2010)
Cátedra de Seguridad Emergencias y Catástrofes de la Universidad de Málaga: VIII Jornadas sobre Seguridad, Emergencias y Catástrofes (2014). http://www.umaemergencias.es/formacion-y-actividades/jornadas-seguridademergencias-y-catastrofes/viii-jornadas-mayo-2014/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Plaza, V., Gomez-Ruiz, J.A., Mandow, A., Garcia-Cerezo, A. (2015). Multi-layer Perceptrons for Voxel-Based Classification of Point Clouds from Natural Environments. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2015. Lecture Notes in Computer Science(), vol 9095. Springer, Cham. https://doi.org/10.1007/978-3-319-19222-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-19222-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19221-5
Online ISBN: 978-3-319-19222-2
eBook Packages: Computer ScienceComputer Science (R0)