Share Email Print

Proceedings Paper

Target Lock: robust real time adaptive visual tracker
Author(s): M. H. Wahab; F. S. Abas
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Visual tracking is still an open problem because one needs to discriminate between the target object and background under long duration. There is a major problem with conventional adaptive tracking where the target object is incorrectly learnt (adapted) during runtime, resulting in poor performance of tracker. In this paper, we address this problem by proposing validation-update strategy to minimize the error of false patches updating. The classifier we use is based on boosted ensemble of Local Dominant Orientation (LDO). However, since LDO features contain binary values which are unsuitable for classification, we have added a process to the online boosting learning algorithm that permits the two binary values of "0" and "1". We elevate the tracker performance by pairing the classifier with normalized crosscorrelation of patches tracked by Lukas-Kanade tracker. In the experiment conducted, we compare our method with two other state-of-the-art adaptive trackers using BoBot dataset. Our method yields good tracking performance under variety of scenarios set by BoBot dataset.

Paper Details

Date Published: 8 June 2012
PDF: 7 pages
Proc. SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), 833432 (8 June 2012); doi: 10.1117/12.956477
Show Author Affiliations
M. H. Wahab, Multimedia Univ. (Malaysia)
F. S. Abas, Multimedia Univ. (Malaysia)

Published in SPIE Proceedings Vol. 8334:
Fourth International Conference on Digital Image Processing (ICDIP 2012)
Mohamed Othman; Sukumar Senthilkumar; Xie Yi, Editor(s)

© SPIE. Terms of Use
Back to Top