Abstract
Reacting to the rapidly changing application requirements during a robot mission requires an adaptation capability of the real-time system. In this paper we focus on real-time image processing to support navigation, collision avoidance and object recognition. Due to the data dependent run-times of image processing algorithms, classic real-time approaches are not feasible. To exemplary solve this problem the SURF algorithm was adapted to the AnyTime concept and used together with a TaskPair scheduler. To make a real-time system capable of self-adaptation useful parameters need to be found. Based on our research we suggest strategies on how to change parameters appropriately.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Asanza, D.F., Wirnitzer, B.: Improving feature based object recognition in service robotics by disparity map based segmentation. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), pp. 2716–2720. Oct 2010
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3), 346–359 (2008) (Similarity Matching in Computer Vision and Multimedia)
Becker, L.B., Gergeleit, M.: Execution environment for dynamically scheduling real-time tasks. In: Procceedings 22nd IEEE Real-Time Systems Symposium (RTSS) WIP-Session 3–6 Dec 2001
Bout, J., Ihme, T., Wetzelsberger, K.: Map reconstruction based on stereo camera images for motion planning. Eurobot, In (2008)
Evans, C.: Notes on the opensurf library. Technical Report CSTR-09-001, University of Bristol, Jan 2009
Falk, H., Plazar, S., Theiling, H.: Compile time decided instruction cache locking using worst-case execution paths. In: Ha, S., Choi, K., Dutt, N.D., Teich, J. (eds.) Proceedings of the 5th International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), pp. 143–148. ACM, Salzburg, Austria, Sep (2007)
Gergeleit, M., Nett, E.: Scheduling transient overload with the taft scheduler. Fall meeting of GI/ITG special interest group on operating systems, Berlin, Nov (2002)
Hochdorfer, S., Lutz, M., Schlegel, C.: Bearing-only slam in everyday environments using omnidirectional vision. In: IEEE ICRA Workshop on Omnidirectional Robot Vision, vol. 28. Anchorage, Alaska, USA (2010)
Ihme, T., Bade, R.: Method for hierarchical stereo vision for spatial environment modelling supported by motion information. In: Proceedings of Robotik 2004. VDI-Verlag, Munich, Germany, 17–18 June 2004
Ihme, T., Wetzelsberger, K., Speckert, M., Fischer, J.: Real-time image processing based on a task-pair scheduling concept. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5596–5601. May 2011
Liu, J.W.S.: Real-Time Systems, Prentice Hall (2000)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)
Luo, R.C., Kay, M.G.: Multisensor integration and fusion in intelligent systems. IEEE Trans. Syst. Man Cybern. 19(5), 901–931 (1989)
Nett, E., Gergeleit, M.: Preserving real-time behavior in dynamic distributed systems. In: Proceedings of the IASTED International Conference on Intelligent Information Systems 1997 (IIS’97), Grand Bahama Island, The Bahamas, 8–10 Dec 1997
Pfannschmidt, T.: Design and implementation of algorithms for real-time image processing based on known image processing methods. Master’s thesis, Hochschule Mannheim (2010)
Acknowledgments
The authors acknowledge the support of the Landesstiftung Baden-Württemberg and the European Regional Development Fond.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Marschik, N., Speckert, M., Ihme, T. (2012). Towards Adaptive Scheduling for Real-Time Image Processing. In: Levi, P., Zweigle, O., Häußermann, K., Eckstein, B. (eds) Autonomous Mobile Systems 2012. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32217-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-32217-4_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32216-7
Online ISBN: 978-3-642-32217-4
eBook Packages: EngineeringEngineering (R0)