Abstract
We propose an evolutionary approach for egomotion estimation with a 3D TOF camera. It is composed of two main modules plus a preprocessing step. The first module computes the Neural Gas (NG) approximation of the preprocessed camera 3D data. The second module is an Evolution Strategy which performs the task of estimating the motion parameters by searching on the space of linear transformations restricted to the translation and rotation, applied on the codevector sets obtained by the NG for successive camera readings. The fitness function is the matching error between the transformed last set of codevectors and the codevector set corresponding to the next camera readings. In this paper, we report new modifications and improvements of this system and provide several comparisons between our and other well known registration algorithms.
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
Oggier, T., Lehmann, M., Kaufmannn, R., Schweizer, M., Richter, M., Metzler, P., Lang, G., Lustenberger, F., Blanc, N.: An all-solid-state optical range camera for 3D-real-time imaging with sub-centimeter depth-resolution (swissranger). In: Proc. SPIE, vol.Ā 5249, pp. 634ā545 (2003)
Dissanayake, G.: A solution to the simultaneous localization and map building (slam) problem. IEEE Transactions on Robotics and AutomationĀ 17(3), 229ā241 (2001)
Thrun, S.: Robotic Mapping: A Survey. In: Exploring Artificial Intelligence in the New Millenium (2002)
Salvi, J., Matabosch, C., Fofi, D., Forest, J.: A review of recent range image registration methods with accuracy evaluation. Image and Vision ComputingĀ 25(5), 578ā596 (2007)
Villaverde, I., GraƱa, M.: A Hybrid Intelligent System for Robot Ego-Motion Estimation with a 3D Camera. In: Corchado, E., Abraham, A., Pedrycz, W. (eds.) HAIS 2008. LNCS (LNAI), vol.Ā 5271, pp. 657ā664. Springer, Heidelberg (2008)
Villaverde, I., Echegoyen, Z., GraƱa, M.: Neuro-evolutive system for ego-motion estimation with a 3D camera. Australian Journal of Intelligent Information SystemsĀ 10(1), 59ā70 (2008)
Martinetz, T.M., Schulten, K.J.: A neural-gas network learns topologies. In: Proc. International Conference on Artificial Neural Networks, pp. 397ā402. North-Holland, Amsterdam (1991)
Randy, L.H., Sue, E.H.: Practical Genetic algorithms, 2nd edn. Wiley-Interscience, Hoboken (2004)
Besl, P., McKay, H.: A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine IntelligenceĀ 14(2), 239ā256 (1992)
Chow, C.K., Tsui, H.T., Lee, T.: Surface registration using a dynamic genetic algorithm. Pattern RecognitionĀ 37(1), 105ā117 (2004)
Vanco, M., Brunnett, G., Schreiber, T.: A hashing strategy for efficient k -nearest neighbors computation. In: CGI 1999: Proceedings of the International Conference on Computer Graphics, Washington, DC, USA, p. 120. IEEE Computer Society, Los Alamitos (1999)
Zinsser, T., Schnidt, H., Niermann, J.: A refined icp algorithm for robust 3-D correspondences estimation. In: International Conference on Image Processing, pp. 695ā698 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Villaverde, I., GraƱa, M. (2009). An Improved Evolutionary Approach for Egomotion Estimation with a 3D TOF Camera. In: Mira, J., FerrĆ”ndez, J.M., Ćlvarez, J.R., de la Paz, F., Toledo, F.J. (eds) Bioinspired Applications in Artificial and Natural Computation. IWINAC 2009. Lecture Notes in Computer Science, vol 5602. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02267-8_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-02267-8_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02266-1
Online ISBN: 978-3-642-02267-8
eBook Packages: Computer ScienceComputer Science (R0)