A Fast Interest Point Detection Method in SURF Algorithm

SURF알고리듬에서의 고속 특징점 검출 방식

  • Received : 2014.07.03
  • Accepted : 2014.09.30
  • Published : 2015.02.28


In this paper, we propose a fast interest point detection method using SURF algorithm. Since the SURF algorithm needs a great computations to detect the interest points and obtain the corresponding descriptors, it is not suitable for real-time based applications. In order to overcome this problem, the interest point detection step is parallelized by OpenMP and SIMD based on analysis of the scale space representation process and localization one in the step. The simulation results demonstrate that processing speed is enhanced about 55% by applying the proposed method.


Supported by : 한국연구재단


  1. Y.M. Kim, J.M. Kim, "Design and Verification of High-Performance Parallel Processor Hardware for JPEG Encoder," IEMEK J. Embed. Sys. Appl., Vol. 6, No. 2, pp. 100-107, 2011 (in Korea).
  2. Y.H. Lee, J.H. Kim, "ePRO-OMP: A Tool for Performance/Energy PRofiler and Analyzer for OpenMP Applications," IEMEK J. Embed. Sys. Appl., Vol. 6, No. 5, pp. 287-293, 2011 (in Korean).
  3. D.G. Lowe, "Distinctive Image Features from Scale - Invariant Keypoints," International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004.
  4. H. Bay, A. Ess, T. Tuytelaars, L. Van Gool. "Speeded-Up Robust Features (SURF)," Computer Vision and Image Understanding, Vol. 110, No. 3, pp. 346- 359, 2008.
  5. E.S. Na, Y.J. Jeong, "FPGA Implementation of SURF-based Feature extraction and Descriptor generation," Journal of Korea Multimedia Society, Vol. 16, No. 4, pp. 483-492, 2013 (in Korean).
  6. Y.S. Do, Y.J. Jeong, "Hardware Design of SURF-based Feature Extraction and Description for Object Tracking," Journal of The Institute of Electronics Engineers of Korea, Vol. 50, No. 5, pp. 83-93, 2013 (in Korean).
  7. J. Svab, T. Krajnik, J. Faigl, L. Preucil, "FPGA based Speeded Up Robust Features," Proceedings of IEEE International Conference on Technologies for Practical Robot Applications, pp. 35-41, 2009.
  8. T. Sledevic, A. Serackis, "SURF Algorithm Implementation on FPGA," Proceedings of the 13th Biennial Baltic Electronics Conference, pp. 291- 294, 2012.
  9. J.C. Kim, Y.H. Jung, E.S. Park, X. Cui, H.I. Kim, "Development of Fast Feature Detector Using Parallel Processing," Proceedings of Control, Automation, and Systems Symposium, pp. 613-618, 2008 (in Korean).
  10. J.C. Kim, Y.H. Jung, E.S. Park, X. Cui, H.I. Kim, U.Y. Huh, "The Implementation of Fast Object Recognition Using Parallel Processing on CPU and GPU," Journal of Institute of Control, Robotics and Systems, Vol. 15, No. 5, pp. 488-495, 2009.
  11. Y.H. Jung, SIMD Parallel Programming, FREELEC. 2012.
  12. Y.H. Jung, OpenMP Parallel Programming , FREELEC. 2011.
  13. D.B. Kirk, W.W. Hwu, Programming Massively Parallel Processors: A Handon- Approach, NVIDIA. 2010
  14. OpenSURP Library. Available: