The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing

Lars Struyf, Stijn De Beugher, Dong Hoon Van Uytsel, Frans Kanters, Toon Goedemé

Abstract

This paper focuses on a thorough comparison of the two main hardware targets for real-time optimization of a computer vision algorithm: GPU and FPGA. Based on a complex case study algorithm for threaded isle detection, implementation on both hardware targets is compared in terms of resulting time performance, code translation effort, hardware cost, power efficiency and integrateability. A real-life case study as described in this paper is a very useful addition to discussions on a more theoretical level, going beyond artificial experiments. In our experiments, we show the speed-up gained by porting our algorithm to FPGA using manually written VHDL and to a heterogeneous GPU/CPU architecture with the OpenCL language. Also, issues and problems occurring during the code porting are detailed.

References

  1. Asano, S., Maruyama, T., and Yamaguchi, Y. (2009). Performance comparison of fpga, gpu and cpu in image processing. In International Conference on Field Programmable Logic and Applications (FPL), pages 126- 131.
  2. Bay, H., Ess, A., Tuytelaars, T., and Gool, L. V. (2008). Speeded-up robust features (surf). Computer Vision and Image Understanding, 110.
  3. Benedict, G. R., David, K., Perhaad, M., and Dana, S. (2011). Heterogeneous Computing with OpenCL. Morgan Kaupmann.
  4. Cope, B., Cheung, P., Luk, W., and Witt, S. (2005). Have gpus made fpgas redundant in the field of video processing? In Proceedings of IEEE International Conference on Field-Programmable Technology, pages 111-118.
  5. da Silva, B., Braeken, A., D'Hollander, E., Touhafi, A., Cornelis, J., and Lemeire, J. (2013). Performance and toolchain of a combined gpu/fpga desktop. In In Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays (FPGA 7813), pages 274-274, New York, NY, USA. ACM.
  6. Duits, R. and Franken, E. M. (2010a). Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, part I: Linear left-invariant diffusion equations on SE(2). Quarterly of Applied mathematics, AMS, 68:255-292.
  7. Duits, R. and Franken, E. M. (2010b). Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, part I: Nonlinear left-invariant diffusion equations on invertible orientation scores. Quarterly of Applied mathematics, AMS, 68:293-331.
  8. Kalitzin, S. N., Romeny, B. M. H., and Viergever, M. A. (1999). Invertible apertured orientation filters in image analysis. IJCV, 31:145-158.
  9. Khronos (2011). OpenCL - the open standard for parallel programming of heterogeneous systems. Khronos Group.
  10. Kovesi, P. (1999). Image features from phase congruency. Videre: A Journal of Computer Vision Research, 1.
  11. Lowe, D. (2004). Distinctive image features from scale invariant keypoints. International Journal on Computer Vision, 60:91-110.
  12. Tsuchiyama, R., Nakamura, T., Lizuka, T., Asahara, A., and Miki, S. (2009). The OpenCL Programming book. Fixstars.
  13. Tyrrell, J., Mahadevan, V., Tong, R., Brown, E., R.K., R. J., and Roysam, B. (2005). 2-d/3-d model-based method to quantify the complexity of microvasculature imaged by in vivo multiphoton microscopy. Microvascular Research, 70:165-178.
Download


Paper Citation


in Harvard Style

Struyf L., De Beugher S., Van Uytsel D., Kanters F. and Goedemé T. (2014). The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing . In Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS, ISBN 978-989-758-000-0, pages 112-119. DOI: 10.5220/0004730301120119


in Bibtex Style

@conference{peccs14,
author={Lars Struyf and Stijn De Beugher and Dong Hoon Van Uytsel and Frans Kanters and Toon Goedemé},
title={The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing},
booktitle={Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,},
year={2014},
pages={112-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004730301120119},
isbn={978-989-758-000-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,
TI - The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing
SN - 978-989-758-000-0
AU - Struyf L.
AU - De Beugher S.
AU - Van Uytsel D.
AU - Kanters F.
AU - Goedemé T.
PY - 2014
SP - 112
EP - 119
DO - 10.5220/0004730301120119