Abstract
Using GPU processing, it is now possible to develop an evolutionary vision system working at interactive frame rates. Our system uses motion as an important cue to evolve detectors which are able to detect an object when this cue is not available. Object detectors consist of a series of high level operators which are applied to the input image. A matrix of low level point operators are used to recombine the output of the high level operators. With this contribution, we investigate, which image processing operators are most useful for object detection. It was found that the set of image processing operators could be considerably reduced without reducing recognition performance. Reducing the set of operators lead to an increase in speedup compared to a standard CPU implementation.
This is a preview of subscription content, log in via an institution to check access.
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
Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D.: Genetic Programming - An Introduction: On The Automatic Evolution of Computer Programs and Its Applications. Morgan Kaufmann Publishers, San Francisco (1998)
Cagnoni, S.: Evolutionary computer vision: a taxonomic tutorial. In: 8th Int. Conf. on Hybrid Intelligent Systems, pp. 1–6. IEEE Comp. Soc., Los Alamitos (2008)
Ebner, M.: Engineering of computer vision algorithms using evolutionary algorithms. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) Advanced Concepts for Intelligent Vision Systems, Mercure Chateau Chartrons, Bordeaux, France, Berlin, pp. 367–378. Springer, Heidelberg (2009)
Ebner, M.: A real-time evolutionary object recognition system. In: Vanneschi, L., Gustafson, S., Moraglio, A., Falco, I.D., Ebner, M. (eds.) Genetic Programming: Proc. of the 12th Europ. Conf., Tübingen, Germany, pp. 268–279. Springer, Berlin (2009)
Ebner, M.: Towards automated learning of object detectors. In: Applications of Ev. Computation, Proc., Istanbul, Turkey, pp. 231–240. Springer, Berlin (2010)
Ebner, M., Zell, A.: Evolving a task specific image operator. In: Poli, R., Voigt, H.-M., Cagnoni, S., Corne, D., Smith, G.D., Fogarty, T.C. (eds.) Joint Proc. of the 1st Europ. Workshops on Evolutionary Image Analysis, Signal Processing and Telecommunications, Göteborg, Sweden, pp. 74–89. Springer, Berlin (1999)
Fung, J., Mann, S., Aimone, C.: OpenVIDIA: Parallel GPU computer vision. In: Int. Multimedia Conf. Proc. of the 13th annual ACM int. conf. on Multimedia, Singapore, vol. 5, pp. 849–852. ACM, New York (2005)
Fung, J., Tang, F., Mann, S.: Mediated reality using computer graphics hardware for computer vision. In: Proc. of the 6h Int. Symp. on Wearable Computers, pp. 83–89. ACM, New York (2002)
Harris, C., Buxton, B.: Evolving edge detectors with genetic programming. In: Koza, J.R., Goldberg, D.E., Fogel, D.B., Riolo, R.L. (eds.) Genetic Programming, Proc. of the 1st Annual Conf., Stanford University, pp. 309–314. The MIT Press, Cambridge (1996)
Jain, R., Kasturi, R., Schunck, B.G.: Machine Vision. McGraw-Hill, New York (1995)
Johnson, M.P., Maes, P., Darrell, T.: Evolving visual routines. In: Brooks, R.A., Maes, P. (eds.) Artificial Life IV, Proc. of the 4th Int. Workshop on the Synthesis and Simulation of Living Systems, pp. 198–209. The MIT Press, Cambridge (1994)
Katz, A.J., Thrift, P.R.: Generating image filters for target recognition by genetic learning. IEEE Trans. on Pattern Analysis and Machine Intelligence 16(9), 906–910 (1994)
Koza, J.R.: Genetic Programming. In: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge (1992)
Krawiec, K., Bhanu, B.: Visual learning by evolutionary and coevolutionary feature synthesis. IEEE Trans. on Evolutionary Computation 11(5), 635–650 (2007)
Lohmann, R.: Bionische Verfahren zur Entwicklung visueller Systeme. PhD thesis, Technische Universität Berlin, Verfahrenstechnik und Energietechnik (1991)
Miller, J.F.: An empirical study of the efficiency of learning boolean functions using a Cartesian Genetic Programming approach. In: Banzhaf, W., et al. (eds.) Proc. of the Genetic and Evolutionary Computation Conf., pp. 1135–1142. Morgan Kaufmann, San Francisco (1999)
NVIDIA. CUDA. Compute Unified Device Architecture. Version 1.1 (2007)
Poli, R.: Genetic programming for image analysis. In: Koza, J.R., Goldberg, D.E., Fogel, D.B., Riolo, R.L. (eds.) Proc. of the 1st Annual Conf. Genetic Programming, Stanford University, pp. 363–368. The MIT Press, Cambridge (1996)
Rizki, M.M., Tamburino, L.A., Zmuda, M.A.: Evolving multi-resolution feature-detectors. In: Fogel, D.B., Atmar, W. (eds.) Proc. of the 2nd Am. Conf. on Evolutionary Programming, pp. 108–118. Evolutionary Prog. Society (1993)
Rost, R.J.: OpenGL Shading Language, 2nd edn. Addison-Wesley, Upper Saddle River (2006)
Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice Hall, Upper Saddle River (2001)
Trujillo, L., Olague, G.: Synthesis of interest point detectors through genetic programming. In: Proc. of the Genetic and Evolutionary Computation Conf., Seattle, Washington, July 8-12, pp. 887–894. ACM, New York (2006)
Witkin, A.P.: Scale-space filtering. In: Proc. of the 8th Int. Joint Conf. on Artificial Intelligence, Karlsruhe, Germany, pp. 1019–1022 (1983)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ebner, M. (2010). Evolving Object Detectors with a GPU Accelerated Vision System. In: Tempesti, G., Tyrrell, A.M., Miller, J.F. (eds) Evolvable Systems: From Biology to Hardware. ICES 2010. Lecture Notes in Computer Science, vol 6274. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15323-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-15323-5_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15322-8
Online ISBN: 978-3-642-15323-5
eBook Packages: Computer ScienceComputer Science (R0)