Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters

Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kämäräinen, Jiri Matas

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

93 Citations (Scopus)
82 Downloads (Pure)

Abstract

Standard RGB-D trackers treat the target as a 2D structure, which makes modelling appearance changes related even to out-of-plane rotation challenging. This limitation is addressed by the proposed long-term RGB-D tracker called OTR – Object Tracking by Reconstruction. OTR performs online 3D target reconstruction to facilitate robust learning of a set of view-specific discriminative correlation filters (DCFs). The 3D reconstruction supports two performance- enhancing features: (i) generation of an accurate spatial support for constrained DCF learning from its 2D projection and (ii) point-cloud based estimation of 3D pose change for selection and storage of view-specific DCFs which robustly localize the target after out-of-view rotation or heavy occlusion. Extensive evaluation on the Princeton RGB-D tracking and STC Benchmarks shows OTR outperforms the state-of-the-art by a large margin.
Original languageEnglish
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
ISBN (Electronic)978-1-7281-3293-8
ISBN (Print)978-1-7281-3294-5
Publication statusPublished - Jun 2019
Publication typeA4 Article in conference proceedings
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition -
Duration: 1 Jan 2000 → …

Publication series

NameIEEE/CVF Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR
Period1/01/00 → …

Publication forum classification

  • Publication forum level 2

Fingerprint

Dive into the research topics of 'Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters'. Together they form a unique fingerprint.

Cite this