UTILIZATION AND PERFORMANCE CONSIDERATIONS IN RESOURCE OPTIMIZED STEREO MATCHING FOR REAL-TIME RECONFIGURABLE HARDWARE

Fredrik Ekstrand, Carl Ahlberg, Mikael Ekström, Lars Asplund, Giacomo Spampinato

Abstract

This paper presents a quantitative evaluation of a set of approaches for increasing the accuracy of an area-based stereo matching method. It is targeting real-time FPGA systems focused on low resource usage and maximized improvement per cost unit to enable concurrent processing. The approaches are applied to a resource optimized correspondence implementation and the individual and cumulative costs and improvements are assessed. A combination of the implemented approaches perform close to other area-matching implementations, but at substantially lower resource usage. Additionally, the limitation in image size associated with standard methods is removed. As fully piped complete on-chip solutions, all improvements are highly suitable for real-time stereo-vision systems.

References

  1. Ahlberg, C., Spampinato, G., Lidholm, J., Ekstrand, F., Ekström, M., and Asplund, L. (2011). Gimme - a general image multiview manipulation engine. Technical paper, School of Innovation Design and Engineering, Mälardalen University.
  2. Arias-Estrada, M. and Xicotencatl, J. (2001). Multiple stereo matching using an extended architecture. In Brebner, G. and Woods, R., editors, FieldProgrammable Logic and Applications, volume 2147 of Lecture Notes in Computer Science, pages 203- 212. Springer Berlin / Heidelberg.
  3. Ekstrand, F., Ahlberg, C., Ekström, M., Asplund, L., and Spampinato, G. (2011). Resource limited hardwarebased stereo matching for high-speed vision system. In 5th International Conference on Automation Robotics and Applications, 2011. (ICARA 2011).
  4. Evaluation, M. U. O. S. (2011). http://vision.middlebury.ed u/stereo.
  5. Fua, P. (2004). A parallel stereo algorithm that produces dense depth maps and preserves image features * ii id ii ii / i i 111 ? 1 1 1 1. Machine Vision and Applications, 6(1993):35-49.
  6. Fusiello, A., Roberto, V., and Trucco, E. (1997). Experiments with a new area-based stereo algorithm.
  7. Kanade, T. and Okutomi, M. (1994). A stereo matching algorithm with an adaptive window: theory and experiment. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 16(9):920 -932.
  8. Lazaros, N., Sirakoulis, G. C., and Gasteratos, A. (2008). Review of stereo vision algorithms: From software to hardware. International Journal of Optomechatronics, 2(4):435-462.
  9. Lidholm, J., Ekstrand, F., and Asplund, L. (2008). Two camera system for robot applications; navigation. In 13th IEEE International Conference on Emerging Technologies and Factory Automation, 2008. (ETFA 2008), pages 345-352. IEEE.
  10. Muhlmann, K., Maier, D., Hesser, J., and Manner, R. (2002). Calculating dense disparity maps from color stereo images, an efficient implementation. International Journal of Computer Vision, 47(1):30-36.
  11. Scharstein, D. and Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47:7-42.
  12. Sunghwan, L., Jongsu, Y., and Junseong, K. (2005). Realtime stereo vision on a reconfigurable system. Lecture Notes in Computer Science, 3553:299-307.
  13. Vega-Rodrguez, M. A., Snchez-Prez, J. M., and GmezPulido, J. A. (2007). An fpga-based implementation for median filter meeting the real-time requirements of automated visual inspection systems. In Proceedings of the 10th IEEE Mediterranean Conference on Control and Automation MED 02. Citeseer.
Download


Paper Citation


in Harvard Style

Ekstrand F., Ahlberg C., Ekström M., Asplund L. and Spampinato G. (2012). UTILIZATION AND PERFORMANCE CONSIDERATIONS IN RESOURCE OPTIMIZED STEREO MATCHING FOR REAL-TIME RECONFIGURABLE HARDWARE . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-04-4, pages 415-418. DOI: 10.5220/0003867404150418


in Bibtex Style

@conference{visapp12,
author={Fredrik Ekstrand and Carl Ahlberg and Mikael Ekström and Lars Asplund and Giacomo Spampinato},
title={UTILIZATION AND PERFORMANCE CONSIDERATIONS IN RESOURCE OPTIMIZED STEREO MATCHING FOR REAL-TIME RECONFIGURABLE HARDWARE},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={415-418},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003867404150418},
isbn={978-989-8565-04-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)
TI - UTILIZATION AND PERFORMANCE CONSIDERATIONS IN RESOURCE OPTIMIZED STEREO MATCHING FOR REAL-TIME RECONFIGURABLE HARDWARE
SN - 978-989-8565-04-4
AU - Ekstrand F.
AU - Ahlberg C.
AU - Ekström M.
AU - Asplund L.
AU - Spampinato G.
PY - 2012
SP - 415
EP - 418
DO - 10.5220/0003867404150418