Skip to main content
SpringerLink
Log in

An enhanced SURF algorithm based on new interest point detection procedure and fast computation technique

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

In this paper, we propose an enhanced Speeded Up Robust Features (eSURF) algorithm to save memory and increase the operating speed. From analysis and observation of the conventional SURF algorithm, we show that a large amount of memory is inefficiently used to detect interest points and considerable operations are repeatedly performed when generating the descriptors of interest points. In the proposed algorithm, the scale-space representation (SSR) step and location (LOC) step are unified based on an efficient memory allocation technique to remove unnecessary memory. In addition, operations for Haar wavelet responses (HWRs) in horizontal and vertical directions, which occupy a major portion of computational loads, are performed by using a fast computation technique in which redundant calculations and repeated memory accesses are efficiently eliminated. Simulation results demonstrate that the proposed eSURF algorithm achieves a time savings of approximately 30 % and a memory savings of approximately 35.7 %, while the feature extraction performance of the proposed eSURF algorithm is exactly identical to that of the conventional SURF algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Speeded-up robust features (SURF). Compt. Vis. Image Underst. 110(3), 346–359 (2008). doi:10.1016/j.cviu.2007.09.014

    Article  Google Scholar 

  2. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Article  Google Scholar 

  3. Zhang, N.: Computing optimized parallel speed-up robust features on multi-core processors. Int. J. Parallel Prog. 38(2), 138–158 (2010). doi:10.1007/s10766-009-0122-9

    Article  MATH  Google Scholar 

  4. Li, E., Yang, L., Wang, B., Li, J., Peng, P.: SURF cascade face detection acceleration on Sandy Bridge Processor. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 41–47 (2012). doi:10.1109/CVPRW.2012.6238893

  5. Hidalgo-Paniagua, A., Vega-Rodriguez, M.A., Pavon, N., Ferruz, J.: A comparative study of parallel software SURF implementations. Concur. Comput. Pract. Exp. 26, 2758–2771 (2014). doi:10.1002/cpe.3163

    Article  Google Scholar 

  6. Kim, D., Kim, M., Kim, K., Sung, M., Ro, W.: Dynamic load balancing of parallel SURF with vertical partitioning. IEEE Trans. Parallel Distrib. Syst. (2014). doi:10.1109/TPDS.2014.2372763

    Google Scholar 

  7. Schaeferling, M., Kiefer, G.: Object recognition on a chip: a complete SURF-based system on a single FPGA. In: International Conference on Reconfigurable Computing and FPGAs, pp. 49–54 (2011)

  8. Schaeferling, M., Hornung, U., Kiefer, G.: Object recognition and pose estimation on embedded hardware: SURF-based system designs accelerated by FPGA logic. Int. J. Reconfigurable Comput. (2012). doi:10.1155/2012

    Google Scholar 

  9. Fan, X., Wu, C., Cao, W., Zhou, X., Wang, S., Wang, L.: Implementation of high performance hardware architecture of OpenSURF algorithm on FPGA. In: International Conference on Field-Programmable Technology, pp. 152–159 (2013). doi:10.1109/FPT.2013.6718346

  10. Lee, S.S., Jang, S.J., Kim, J., Hwang, Y., Choi, B.: Memory-efficient SURF architecture for ASIC implementation. Electron. Lett. 50(15), 1058–1059 (2014)

    Article  Google Scholar 

  11. Han, B., Wang, Y., Jia, X.: Fast calculating feature point’s main orientation in SURF algorithm. In: International Conference on Computer, Mechatronics, Control and Electronic Engineering, pp. 165–168 (Aug. 2010). doi:10.1109/CMCE.2010.5609874

  12. Evans, C.: Notes on the OpenSURF library. Technical Report, CSTR-09-001, University of Bristol, UK, 2009. http://www.chrisevansdev.com

  13. Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)

    Article  Google Scholar 

  14. Aly, M., Welinder, P., Munich, M., Perona, P.,: Towards automated large scale discovery of image families. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 9–16 (2009). http://www.vision.caltech.edu/malaa/datasets/caltech-buildings/

  15. Nister, D., Stewenius, H.,: Scalable recognition with a vocabulary tree. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, pp. 2161–2168 (2006). http://www.vis.uky.edu/∼stewe/ukbench/

Download references

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2014R1A12056434).

Author information

Authors and Affiliations

  1. Department of Aerospace Engineering, Gyeongsang National University, 501 Jinju-daero, Jinju, 52828, Republic of Korea

    Seung Hyeon Cheon

  2. Department of Electronics Engineering, Pusan National University, 2 Busandaehak-Ro 63 Beon-Gil, Pusan, 46241, Republic of Korea

    Il Kyu Eom

  3. Department of Aerospace and Software Engineering/ERI, Gyeongsang National University, 501 Jinju-daero, Jinju, 52828, Republic of Korea

    Seok Wun Ha & Yong Ho Moon

Authors
  1. Seung Hyeon Cheon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Il Kyu Eom
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Seok Wun Ha
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yong Ho Moon
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yong Ho Moon.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cheon, S.H., Eom, I.K., Ha, S.W. et al. An enhanced SURF algorithm based on new interest point detection procedure and fast computation technique. J Real-Time Image Proc 16, 1177–1187 (2019). https://doi.org/10.1007/s11554-016-0614-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-016-0614-y

Keywords

Search

Navigation