Robust visual tracking based on Informative random fern

DOI

10.2991/iccsae-15.2016.128How to use a DOI?

Keywords

Visual tracking; IRF-TLD; Gaussian projection; Real time

Abstract

In this paper, a novel visual tracking algorithm named as Informative random fern - Tracking Learning Detection (IRF-TLD) has been proposed. Instead of a binary comparison in the standard random fern of TLD, we use the real value feature and Gaussian random projection to acquire the advantages of high accuracy and low memory requirement. Experimental results on challenging sequences have demonstrated the superior performance of our IRF-TLD when compared with several state-of-the-art tracking algorithms.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hao Dong
AU  - Rui Wang
PY  - 2016/02
DA  - 2016/02
TI  - Robust visual tracking based on Informative random fern
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 689
EP  - 693
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.128
DO  - 10.2991/iccsae-15.2016.128
ID  - Dong2016/02
ER  -