Abstract
Intelligent sensors for mobile robots play an important role in many technical applications. In this paper a real-time image recognition system for a tiny autonomous mobile robot is presented, capable of detecting objects in real-time at a frame rate of up to 60 frames/s. The image recognition module has very low power consumption of less than 250 mW and fits into a package of only 35 × 35 mm including a CMOS camera and a low power, high performance signal processor. We propose an object recognition algorithm that is optimized for deeply embedded systems used in energy and performance constrained devices. The algorithm is based on a combination of edge and color detection and uses a fixed model for each object to be recognized. Results of the ball recognition application show that its relative polar coordinates are found within 11 ms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alloimonos, J. Y., Weiss, L., and Bandyopadhyay, A. 1987. Active vision. In Proceedings 1st ICCV, IEEE Press, London, UK, pp. 35–54.
Biribauer, M. 2002. Ein Bildverarbeitungssystem zur Navigation mobiler Roboter. Vienna University of Technology, Diploma Thesis, March (German).
Blackfin BF5xx found at: http://www.analog.com/blackfin
Dudek, G., and Jenkin, M. 2000. Computational Principles of Mobile Robotics. New York: Cambridge University Press, ISBN 0-521-56876-5.
GAO, Q., Hong, B., Hu, D., and XIAO, S. 2003. Study on navigation of small-size autonomous robot based on coordination of iso-vision system with two cameras. In FIRA Robot World Congress 2003, Vienna, Austria.
Harris, L., and Jenkin, M. 1998. Vision and Action. New York: Cambridge University Press.
Information about Hondas ASIMO robot can be found at: http://world.honda.com/ASI
Information on the MiroSot league can be found at: http://www.fira.net/soccer/mirosot/overview.html
Information about Spirit can be found at: http://marsrovers.jpl.nasa.gov/home/index.html
Information about Sony’s QRIO can be found at: http://www.sony.net/Products/qrio/
Information about Sony’s AIBO can be found at: http://www.sony.net/Products/aibo/
Jamzad, M., Sadjad, B. S., Mirrokni, V. S., Kazemi, M., Chitsaz, H., Heydarnoori, A., Hajiaghai, M. T., and Chiniforoosha, E. 2001. A Fast Vision System for Middle Size Robots in RoboCup, RoboCup 2001, Robot Soccer World Cup V, Springer Verlag, pp. 71–80.
Jung, M. J., Jang, J. S., and Kim, J. H. 2001. Development of RoboSot category soccer robots. Journal of Harbin Institute of Technology 8(3).
Motorola MC9328MXL: http://www.motorola.com/
Narikiyo, K., Justan, M. P., Alano, N. F. 2003. Image-processing controlled mobile robot. In FIRA Robot World Congress 2003, Vienna, Austria.
Novak, G. 2002. Multi agent systems—Robot soccer. Vienna University of Technology, PhD theses, April.
Official RoboCup Homepage can be found at: http://www.roboocup.org
Rowe, A., Rosenberg, C., and Nourbakhsh, I. 2001. A simple low cost color vision system, Tech Sketch Paper Presented at CVPR.
Russ, J. C. 2003. The Image Processing Handbook, fourth edition. Vol. 744, pp. 242–255.
Russ, J. C. 2003. The Image Processing Handbook, fourth edition. Vol. 744, pp. 641–645
Sargent, R., Bailey, B., Witty, C., and Wright, A. 1997. Dynamic object capture using fast vision tracking. AI Magazine 18(1).
Schulenburg, E. 2003. Selbstlokalisierung im Roboter-Fußball unter Verwendung einer omnidirektionalen Kamera, Diploma Work, Freiburg (German).
Texas Instruments TSM320C5502 found at: http://www.ti.com/dsp
The Homepage of the Tinyphoon robot can be found at: http://www.tinyphoon.com
Xilinx Spartan-3 FPGA found at: http://www.xilinx.com
Author information
Authors and Affiliations
Corresponding author
Additional information
Stefan Mahlknecht received a Master’s degree in electrical engineering and a doctoral degree from Vienna University of technology. His doctoral thesis dealt with the topic of energy selfsufficient wireless sensor networks. He spend one year at the University of Illinois in Urbana Champain, where he focused on communication networks and protocols. Since 2001 he is a member of the departements staff. His research interests are devoted to the topic of wireless sensor networks, communication protocols, embedded systems and robotics.
Roland Oberhammer is a master thesis student at the Institute of Computer Technology at the Vienna University of Technology. His master thesis dealt with the topic of real-time ball recognition on resource limited embedded platforms. His research interests are in the field of embedded systems and robotics.
Gregor Novak received a Master’s degree in mechanical engineering and a doctoral degree in technical sciences both from the Vienna University of Technology in Austria in the years 1997 and 2002, respectively as well as a Master’s degree in engineering management in 2001 from Oakland University in USA. Presently he is the coordinator of the Vienna University of Technologys Center of Excellence for Autonomous Systems. His research focuses on autonomous mobile cooperating robots.
Rights and permissions
About this article
Cite this article
Mahlknecht, S., Oberhammer, R. & Novak, G. A Real-Time Image Recognition System for Tiny Autonomous Mobile Robots. Real-Time Syst 29, 247–261 (2005). https://doi.org/10.1007/s11241-005-6887-8
Issue Date:
DOI: https://doi.org/10.1007/s11241-005-6887-8