Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kamarainen, Jiri Matas; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1339-1348

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Kart_2019_CVPR,
author = {Kart, Ugur and Lukezic, Alan and Kristan, Matej and Kamarainen, Joni-Kristian and Matas, Jiri},
title = {Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}