Discriminative multi-task sparse learning for robust visual tracking using conditional random field

Seyed Bozorgtabar, Roland GOECKE

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    In this paper, we propose a discriminative multitask sparse learning scheme for object tracking in a particle filter framework. By representing each particle as a linear combination of adaptive dictionary templates, we utilise the correlations among different particles (tasks) to obtain a better representation and a more efficient scheme than learning each task individually. However, this model is completely generative and the designed tracker may not be robust enough to prevent the drifting problem in the presence of rapid appearance changes. In this paper, we use a Conditional Random Field (CRF) along with the multitask sparse model to extend our scheme to distinguish the object candidate from the background particle candidate. By this way, the number of particle samples is reduced significantly, while we make the tracker more robust. The proposed algorithm is evaluated on 11 challenging sequences and the results confirm the effectiveness of the approach and significantly outperforms the state-of-the-art trackers in terms of accuracy measures including the centre location error and the overlap ratio, respectively.
    Original languageEnglish
    Title of host publication2014 International Conference on Digital Image Computing
    Subtitle of host publicationTechniques and Applications, DICTA 2014
    EditorsAbdesselam Bouzerdoum, Lei Wang, Philip Ogunbona, Wanqing Li, Son Lam Phung
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-8
    Number of pages8
    ISBN (Electronic)9781479954094
    ISBN (Print)9781479954094
    DOIs
    Publication statusPublished - 2015
    Event2014 International Conference on Digital Image Computing, Techniques and Applications - Wollongong, Wollongong, Australia
    Duration: 25 Nov 201427 Nov 2014

    Publication series

    Name2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014

    Conference

    Conference2014 International Conference on Digital Image Computing, Techniques and Applications
    Abbreviated titleDICTA 2014
    CountryAustralia
    CityWollongong
    Period25/11/1427/11/14

    Fingerprint

    Glossaries

    Cite this

    Bozorgtabar, S., & GOECKE, R. (2015). Discriminative multi-task sparse learning for robust visual tracking using conditional random field. In A. Bouzerdoum, L. Wang, P. Ogunbona, W. Li, & S. L. Phung (Eds.), 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014 (pp. 1-8). [7008102] (2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2014.7008102
    Bozorgtabar, Seyed ; GOECKE, Roland. / Discriminative multi-task sparse learning for robust visual tracking using conditional random field. 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014. editor / Abdesselam Bouzerdoum ; Lei Wang ; Philip Ogunbona ; Wanqing Li ; Son Lam Phung. USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 1-8 (2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014).
    @inproceedings{2cdeaa4a76844f65a7bde21c78133f8a,
    title = "Discriminative multi-task sparse learning for robust visual tracking using conditional random field",
    abstract = "In this paper, we propose a discriminative multitask sparse learning scheme for object tracking in a particle filter framework. By representing each particle as a linear combination of adaptive dictionary templates, we utilise the correlations among different particles (tasks) to obtain a better representation and a more efficient scheme than learning each task individually. However, this model is completely generative and the designed tracker may not be robust enough to prevent the drifting problem in the presence of rapid appearance changes. In this paper, we use a Conditional Random Field (CRF) along with the multitask sparse model to extend our scheme to distinguish the object candidate from the background particle candidate. By this way, the number of particle samples is reduced significantly, while we make the tracker more robust. The proposed algorithm is evaluated on 11 challenging sequences and the results confirm the effectiveness of the approach and significantly outperforms the state-of-the-art trackers in terms of accuracy measures including the centre location error and the overlap ratio, respectively.",
    keywords = "Visual Tracking, Image processing",
    author = "Seyed Bozorgtabar and Roland GOECKE",
    year = "2015",
    doi = "10.1109/DICTA.2014.7008102",
    language = "English",
    isbn = "9781479954094",
    series = "2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    pages = "1--8",
    editor = "Abdesselam Bouzerdoum and Lei Wang and Philip Ogunbona and Wanqing Li and Phung, {Son Lam}",
    booktitle = "2014 International Conference on Digital Image Computing",
    address = "United States",

    }

    Bozorgtabar, S & GOECKE, R 2015, Discriminative multi-task sparse learning for robust visual tracking using conditional random field. in A Bouzerdoum, L Wang, P Ogunbona, W Li & SL Phung (eds), 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014., 7008102, 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 1-8, 2014 International Conference on Digital Image Computing, Techniques and Applications, Wollongong, Australia, 25/11/14. https://doi.org/10.1109/DICTA.2014.7008102

    Discriminative multi-task sparse learning for robust visual tracking using conditional random field. / Bozorgtabar, Seyed; GOECKE, Roland.

    2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014. ed. / Abdesselam Bouzerdoum; Lei Wang; Philip Ogunbona; Wanqing Li; Son Lam Phung. USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 1-8 7008102 (2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014).

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Discriminative multi-task sparse learning for robust visual tracking using conditional random field

    AU - Bozorgtabar, Seyed

    AU - GOECKE, Roland

    PY - 2015

    Y1 - 2015

    N2 - In this paper, we propose a discriminative multitask sparse learning scheme for object tracking in a particle filter framework. By representing each particle as a linear combination of adaptive dictionary templates, we utilise the correlations among different particles (tasks) to obtain a better representation and a more efficient scheme than learning each task individually. However, this model is completely generative and the designed tracker may not be robust enough to prevent the drifting problem in the presence of rapid appearance changes. In this paper, we use a Conditional Random Field (CRF) along with the multitask sparse model to extend our scheme to distinguish the object candidate from the background particle candidate. By this way, the number of particle samples is reduced significantly, while we make the tracker more robust. The proposed algorithm is evaluated on 11 challenging sequences and the results confirm the effectiveness of the approach and significantly outperforms the state-of-the-art trackers in terms of accuracy measures including the centre location error and the overlap ratio, respectively.

    AB - In this paper, we propose a discriminative multitask sparse learning scheme for object tracking in a particle filter framework. By representing each particle as a linear combination of adaptive dictionary templates, we utilise the correlations among different particles (tasks) to obtain a better representation and a more efficient scheme than learning each task individually. However, this model is completely generative and the designed tracker may not be robust enough to prevent the drifting problem in the presence of rapid appearance changes. In this paper, we use a Conditional Random Field (CRF) along with the multitask sparse model to extend our scheme to distinguish the object candidate from the background particle candidate. By this way, the number of particle samples is reduced significantly, while we make the tracker more robust. The proposed algorithm is evaluated on 11 challenging sequences and the results confirm the effectiveness of the approach and significantly outperforms the state-of-the-art trackers in terms of accuracy measures including the centre location error and the overlap ratio, respectively.

    KW - Visual Tracking

    KW - Image processing

    UR - http://www.scopus.com/inward/record.url?scp=84922570892&partnerID=8YFLogxK

    UR - http://www.mendeley.com/research/discriminative-multitask-sparse-learning-robust-visual-tracking-using-conditional-random-field

    U2 - 10.1109/DICTA.2014.7008102

    DO - 10.1109/DICTA.2014.7008102

    M3 - Conference contribution

    SN - 9781479954094

    T3 - 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014

    SP - 1

    EP - 8

    BT - 2014 International Conference on Digital Image Computing

    A2 - Bouzerdoum, Abdesselam

    A2 - Wang, Lei

    A2 - Ogunbona, Philip

    A2 - Li, Wanqing

    A2 - Phung, Son Lam

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - USA

    ER -

    Bozorgtabar S, GOECKE R. Discriminative multi-task sparse learning for robust visual tracking using conditional random field. In Bouzerdoum A, Wang L, Ogunbona P, Li W, Phung SL, editors, 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014. USA: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 1-8. 7008102. (2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014). https://doi.org/10.1109/DICTA.2014.7008102