DYNAMIC KEYPOINT-BASED ALGORITHM OF OBJECT TRACKING

A. I. Morgacheva, V. A. Kulikov, V. P. Kosykh

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

The model of the observed object plays the key role in the task of object tracking. Models as a set of image parts, in particular, keypoints, is more resistant to the changes in shape, texture, angle of view, because local changes apply only to specific parts of the object. On the other hand, any model requires updating as the appearance of the object changes with respect to the camera. In this paper, we propose a dynamic (time-varying) model, based on a set of keypoints. To update the data this model uses the algorithm of rating keypoints and the decision rule, based on a Function of Rival Similarity (FRiS). As a result, at the test set of image sequences the improvement was achieved on average by 9.3% compared to the original algorithm. On some sequences, the improvement was 16% compared to the original algorithm.

Original languageEnglish
Title of host publicationINTERNATIONAL WORKSHOP PHOTOGRAMMETRIC AND COMPUTER VISION TECHNIQUES FOR VIDEO SURVEILLANCE, BIOMETRICS AND BIOMEDICINE
EditorsS Zheltov, Y Vizilter, Knyaz
PublisherCopernicus Gesellschaft mbH
Pages79-82
Number of pages4
DOIs
Publication statusPublished - May 2017
EventInternational Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine - Moscow
Duration: 15 May 201717 May 2017

Publication series

NameInternational Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences
PublisherCOPERNICUS GESELLSCHAFT MBH
Volume42-2
ISSN (Print)2194-9034

Conference

ConferenceInternational Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine
CityMoscow
Period15.05.201717.05.2017

Keywords

  • Tracking
  • Keypoints
  • Dynamic object model
  • FRiS

Cite this