Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking

In this paper, we propose an efficient and accurate visual tracker equipped with a new particle filtering algorithm and robust subspace learning-based appearance model. The proposed visual tracker avoids drifting problems caused by abrupt motion changes and severe appearance variations that are well...

Full description

Bibliographic Details
Main Authors: Kim, Du Yong, Jeon, M.
Format: Journal Article
Published: IEEE 2013
Online Access:http://hdl.handle.net/20.500.11937/56045
_version_ 1848759772173565952
author Kim, Du Yong
Jeon, M.
author_facet Kim, Du Yong
Jeon, M.
author_sort Kim, Du Yong
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose an efficient and accurate visual tracker equipped with a new particle filtering algorithm and robust subspace learning-based appearance model. The proposed visual tracker avoids drifting problems caused by abrupt motion changes and severe appearance variations that are well-known difficulties in visual tracking. The proposed algorithm is based on a type of auxiliary particle filtering that uses a spatio-temporal sliding window. Compared to conventional particle filtering algorithms, spatio-temporal auxiliary particle filtering is computationally efficient and successfully implemented in visual tracking. In addition, a real-time robust principal component pursuit (RRPCP) equipped with l 1 -norm optimization has been utilized to obtain a new appearance model learning block for reliable visual tracking especially for occlusions in object appearance. The overall tracking framework based on the dual ideas is robust against occlusions and out-of-plane motions because of the proposed spatio-temporal filtering and recursive form of RRPCP. The designed tracker has been evaluated using challenging video sequences, and the results confirm the advantage of using this tracker. © 1992-2012 IEEE.
first_indexed 2025-11-14T10:05:11Z
format Journal Article
id curtin-20.500.11937-56045
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:05:11Z
publishDate 2013
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-560452023-08-02T06:39:09Z Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking Kim, Du Yong Jeon, M. In this paper, we propose an efficient and accurate visual tracker equipped with a new particle filtering algorithm and robust subspace learning-based appearance model. The proposed visual tracker avoids drifting problems caused by abrupt motion changes and severe appearance variations that are well-known difficulties in visual tracking. The proposed algorithm is based on a type of auxiliary particle filtering that uses a spatio-temporal sliding window. Compared to conventional particle filtering algorithms, spatio-temporal auxiliary particle filtering is computationally efficient and successfully implemented in visual tracking. In addition, a real-time robust principal component pursuit (RRPCP) equipped with l 1 -norm optimization has been utilized to obtain a new appearance model learning block for reliable visual tracking especially for occlusions in object appearance. The overall tracking framework based on the dual ideas is robust against occlusions and out-of-plane motions because of the proposed spatio-temporal filtering and recursive form of RRPCP. The designed tracker has been evaluated using challenging video sequences, and the results confirm the advantage of using this tracker. © 1992-2012 IEEE. 2013 Journal Article http://hdl.handle.net/20.500.11937/56045 10.1109/TIP.2012.2218824 IEEE restricted
spellingShingle Kim, Du Yong
Jeon, M.
Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title_full Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title_fullStr Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title_full_unstemmed Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title_short Spatio-temporal auxiliary particle filtering with l1-Norm- Based Appearance Model Learning for Robust Visual Tracking
title_sort spatio-temporal auxiliary particle filtering with l1-norm- based appearance model learning for robust visual tracking
url http://hdl.handle.net/20.500.11937/56045