Skip to main content
SpringerLink
Log in

GPU-based parallel optimization for real-time scale-invariant feature transform in binocular visual registration

  • Original Article
  • Published:
Personal and Ubiquitous Computing Aims and scope Submit manuscript

Abstract

Scale-invariant feature transform (SIFT) is one of the widely used interest point features. It has been successfully applied in various computer vision algorithms like object detection, object tracking, robotic mapping, and large-scale image retrieval. Although SIFT descriptor is highly robust towards scale and rotation variations, the high computational complexity of the SIFT algorithm inhibits its use in applications demanding real-time response and in algorithms dealing with very large-scale databases. In order to be effective for image matching process in near real-time, the Compute Unified Device Architecture (CUDA) application programming interface of a graphics processing unit (GPU) is incorporated to speed up or improve the SIFT method. Experimental results show that the proposed GPU-based SIFT framework is suitable for image application in real time. It can improve the image matching process both in time and accuracy compared with conventional SIFT method.

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

Similar content being viewed by others

References

  1. Li Z, Jia H, Zhang Y (2017). HartSift: A high-accuracy and real-time SIFT based on GPU[C]. IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS). IEEE Computer Society.

  2. Lalonde M, Byrns D, Gagnon L et al (2007) Real-time eye blink detection with GPU-based SIFT tracking[C]. IEEE Fourth Canadian Conference on Computer and Robot Vision (CRV ’07). 

  3. Warn S, Emeneker W, Cothren J, Apon A (2009) Accelerating SIFT on parallel architectures[C]. IEEE International Conference on Cluster Computing and Workshops

  4. Fassold H, Rosner J (2015) A real-time GPU implementation of the SIFT algorithm for large-scale video analysis tasks[C]. Real-Time Image and Video Processing 2015. International Society for Optics and Photonics

  5. Wang G, Rister B, Cavallaro JR (2013) Workload analysis and efficient OpenCL-based implementation of SIFT algorithm on a smartphone[C]. 2013 IEEE Global Conference on Signal and Information Processing

  6. Acharya KA, Babu RV (2013) Speeding up SIFT using GPU[C]. IEEE Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)

  7. Mohammadi MS, Rezaeian M (2014) Towards affordable computing: SiftCU a simple but elegant GPU-based implementation of SIFT[J]. Int J Comput Appl 90(7):30–37

  8. Acharya KA, Venkatesh Babu R, Vadhiyar SS (2018) A real-time implementation of SIFT using GPU[J]. J Real-Time Image Process 14(2):267–277

  9. Jiang C, Geng ZX, Wei XF, et al (2013) SIFT implementation based on GPU[C]. International Symposium on Photoelectronic Detection and Imaging 2013: Optical Storage and Display Technology. Int Soc Optics Photonics

  10. Zhan ZF, Li G, Zhang XH (2014) Research on SIFT matching algorithm based on GPU[J]. Appl Mech Mater 599–601:1652–1656

  11. Dadi EW, Daoudi EM (2014) GPU-based for accelerating the BF-SIFT method for large scale 3D shape retrieval[C]. IEEE International Conference on Multimedia Computing & Systems.

  12. Lee C, Rhee CE, Lee H (2017) Complexity reduction by modified scale-space construction in SIFT generation optimized for a mobile GPU[J]. In IEEE Transactions on Circuits and Systems for Video Technology 27(10):2246–2259

  13. Daðason K, Lejsek H, Jóhannsson ÁÞ et al (2010) GPU acceleration of Eff2 descriptors using CUDA[C]. ACM International Conference on Multimedia

  14. Jiang J, Li X, Zhang G (2014) SIFT Hardware Implementation for Real-Time Image Feature Extraction[J]. In IEEE Transactions on Circuits and Systems for Video Technology 24(7):1209–1220

  15. Kumar RP, Muknahallipatna SS, Mcinroy JE (2014) SIFTs scale-space extrema detection on GPU for real-time applications (WIP)[C]. Summer Simulation Multiconference. Soci Comp Simulation Int

  16. Kusamura Y, Kozawa Y, Amagasa T, Kitagawa H (2016) GPU Acceleration of content-based image retrieval based on SIFT descriptors[C]. 19th International Conference on Network-Based Information Systems (NBiS), Ostrava, 2016, pp 342–347

  17. Donglin J, Jianzhi L, Wanwan Y, Ye J (2015) Parallel realization of SIFT feature abstraction based on GPU using TEGRA K1[C]. IET International Radar Conference 2015, Hangzhou, 2015, pp 1–4

  18. Cheng J, Zhu X, Ding W, Gao G (2016) A robust real-time indoor navigation technique based on GPU-accelerated feature matching[C]. 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN), Alcala de Henares, 2016, pp 1–4

  19. Rister B, Wang G, Wu, Cavallaro JR (2013) A fast and efficient sift detector using the mobile GPU[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, 2013, pp. 2674–2678

  20. Sun Y, Zhao L, Huang S, Yan L, Dissanayake G (2014) L2-SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry[J]. ISPRS Journal of Photogrammetry and Remote Sensing, volume 91, 2014, pp 1–16

  21. Warn S, Apon A, Cothren J (2011) Accelerating SIFT on hybrid clusters. In Proceedings of the ACM SIGSPATIAL Second International Workshop on High Performance and Distributed Geographic Information Systems (HPDGIS ’11)

  22. Bhangale U, Durbha S (2015) High performance SIFT features clustering of VHR satellite images for disaster management[C]. In Proceedings of the Third International Symposium on Women in Computing and Informatics (WCI ’15), Indu Nair (Ed.). ACM, New York, p 324–329

Download references

Author information

Authors and Affiliations

  1. College of Electrical Engineering, Zhejiang University, Hangzhou, China

    Jiashen Li

  2. College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China

    Yun Pan

Authors
  1. Jiashen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yun Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiashen Li.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, J., Pan, Y. GPU-based parallel optimization for real-time scale-invariant feature transform in binocular visual registration. Pers Ubiquit Comput 23, 465–474 (2019). https://doi.org/10.1007/s00779-019-01222-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00779-019-01222-3

Keywords

Search

Navigation