Publication Details

Depth-Based Filtration for Tracking Boost

CHRÁPEK, D.; BERAN, V.; ZEMČÍK, P. Depth-Based Filtration for Tracking Boost. In Springer International Publishing. Lecture Notes in Computer Science. Lecture Notes in Computer Science. Catania: Springer International Publishing, 2015. p. 217-228. ISBN: 978-3-319-25903-1. ISSN: 0302-9743.
Czech title
Zlepšení sledování prostřednictvím filtrace pomocí hloubkových informací
Type
conference paper
Language
English
Authors
URL
Keywords

Real-time, RGBD, Segmentation, Tracking

Abstract

This paper presents a novel depth information utilization method for performance boosting of tracking in traditional RGB trackers for arbitrary objects (objects not known in advance) by object segmentation/separation supported by depth information. The main focus is on real-time applications, such as robotics or surveillance, where exploitation of depth sensors, that are nowadays affordable, is not only possible but also feasible. The aim is to show that the depth information used for target segmentation significantly helps reducing incorrect model updates caused by occlusion or drifts and improves success rate and precision of traditional RGB tracker while keeping comparably efficient and thus possibly real-time. The paper also presents and discusses the achieved performance results.

Published
2015
Pages
217–228
Journal
Lecture Notes in Computer Science, vol. 9386, no. 9386, ISSN 0302-9743
Proceedings
Springer International Publishing
Series
Lecture Notes in Computer Science
ISBN
978-3-319-25903-1
Publisher
Springer International Publishing
Place
Catania
DOI
UT WoS
000374794500019
EID Scopus
BibTeX
@inproceedings{BUT119922,
  author="David {Chrápek} and Vítězslav {Beran} and Pavel {Zemčík}",
  title="Depth-Based Filtration for Tracking Boost",
  booktitle="Springer International Publishing",
  year="2015",
  series="Lecture Notes in Computer Science",
  journal="Lecture Notes in Computer Science",
  volume="9386",
  number="9386",
  pages="217--228",
  publisher="Springer International Publishing",
  address="Catania",
  doi="10.1007/978-3-319-25903-1\{_}19",
  isbn="978-3-319-25903-1",
  issn="0302-9743",
  url="http://link.springer.com/chapter/10.1007%2F978-3-319-25903-1_19"
}
Back to top