Skip to main content
SpringerLink
Log in

Local Feature Descriptor Indexing for Image Matching and Object Detection in Real-Time Applications

  • SPECIAL ISSUE
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Local feature extraction and description algorithms can be used to address a large variety of computer vision problems, including pattern recognition, frame stitching and 3D reconstruction. One of the most computationally expensive and time-consuming stages of any method based on local features is keypoint matching. This paper discusses possible ways to optimize matching for frame alignment and object detection applications using Vantage-Point tree indexing to optimize pairwise keypoint matching, and image keypoint graph indexing to optimize pose estimation.

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.

Similar content being viewed by others

REFERENCES

  1. S. Krig, Computer Vision Metrics: Survey, Taxonomy, and Analysis (Apress, Berkeley, CA, 2014).

    Book  Google Scholar 

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

    Article  Google Scholar 

  3. E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” in Proc. 2011 IEEE Int. Conf. on Computer Vision (ICCV 2011) (Barcelona, Spain, 2011), IEEE, pp. 2564-2571.

  4. P. N. Yianilos, “Data structures and algorithms for nearest neighbor search in general metric spaces,” in Proc. 4th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA’93) (Austin, TX, USA, 1993) (SIAM, Philadelphia, PA, 1993), pp. 311–321.

Download references

Author information

Authors and Affiliations

  1. Faculty of Radiophysics and Computer Technologies, Belarusian State University, 220030, Minsk, Belarus

    K. Halavataya

Authors
  1. K. Halavataya
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Halavataya.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Halavataya Katsiaryna. Date of birth: 21.07.1993. Education: bachelor honors degree (grad. 2015), master’s degree (grad. 2016), currently PhD student. Affiliation: Belarusian State University, Faculty of Radiophysics and Computer Technologies, Intelligent Systems dept.: Position: Sr. lecturer. Area of research: Computer vision, 3D reconstruction from images, machine learning and deep learning, computer graphics, virtual and augmented reality. Number of publications: 30 articles and conference proceedings materials.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Halavataya, K. Local Feature Descriptor Indexing for Image Matching and Object Detection in Real-Time Applications. Pattern Recognit. Image Anal. 30, 16–21 (2020). https://doi.org/10.1134/S105466182001006X

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S105466182001006X

Keywords:

Search

Navigation