One-Class SVM Assisted Accurate Tracking
Paper i proceeding, 2012

Recently, tracking is regarded as a binary classification problem by discriminative tracking methods. However, such binary classification may not fully handle the outliers, which may cause drifting. In this paper, we argue that tracking may be regarded as one-class problem, which avoids gathering limited negative samples for background description. Inspired by the fact the positive feature space generated by One-Class SVM is bounded by a closed sphere, we propose a novel tracking method utilizing One-Class SVMs that adopt HOG and 2 bit-BP as features, called One-Class SVM Tracker (OCST). Simultaneously an efficient initialization and online updating scheme is also proposed. Extensive experimental results prove that OCST outperforms some state-of-the-art discriminative tracking methods on providing accurate tracking and alleviating serious drifting.

visual tracking

image database retrieval

support vector machine

Författare

Chen Gong

Yu Qiao

Jie Yang

Irene Yu-Hua Gu

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

6th ACM/IEEE Int'l Conf on Distributed Smart Cameras (ICDSC 12), Oct 30 - Nov.2, 2012, Hong Kong

6 pages-

Styrkeområden

Transport

Livsvetenskaper och teknik

Ämneskategorier

Bioinformatik (beräkningsbiologi)

Reglerteknik

Signalbehandling

Datorseende och robotik (autonoma system)

Annan elektroteknik och elektronik

Mer information

Skapat

2017-10-07