Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking

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

    1 Citation (Scopus)

    Abstract

    In this paper we examine two different automated video surveillance techniques for detection and tracking of pedestrians based on fusion of colour and thermal images. The first approach is a novel particle filtering based on Bayesian framework, and the seconf one is an approach based on fusion of shape and appearance cues. The shape and appearance based technique involves a layered two pass scheme, where in the first pass-an expectation-maximization (EM) algorithm is used to separate infrared images into still background and moving foreground layers. In the second pass: shape cues from the first pass is used to eliminate non-pedestrian moving objects and then appearance cue is used to locate the exact position of pedestrians. Then pedestrians are detected by sequential application of templates at multiple scales. For tracking the pedestrian a graph matching-based algorithm which fueses the shape and appearance information was used. The particle filtering based algorithm on other hand is based on building a scene background model with each pixel represented as a multimodal distribution of colour and thermal images. Then this background model is used to build a particle filter for tracking the pedestrian. The particle filter uses a novel formulation of observation likelihoods The evaluation of the two detection and tracking approaches was done by performing experiments on the thermal and colour dataset from OTCBVS database
    Original languageEnglish
    Title of host publicationProceedings of the 2nd International Conference on Signal Processing and Communications
    EditorsBeata J Wysocki, Tadeusz A Wysocki
    Place of PublicationUnited States
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-6
    Number of pages6
    ISBN (Print)9780975693469
    Publication statusPublished - 2008
    Event2nd International Conference on Signal Processing and Communications - Gold Coast, Australia
    Duration: 15 Dec 200817 Dec 2008

    Conference

    Conference2nd International Conference on Signal Processing and Communications
    CountryAustralia
    CityGold Coast
    Period15/12/0817/12/08

    Fingerprint

    Color
    Fusion reactions
    Pixels
    Infrared radiation
    Hot Temperature
    Experiments

    Cite this

    Chetty, G. (2008). Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking. In B. J. Wysocki, & T. A. Wysocki (Eds.), Proceedings of the 2nd International Conference on Signal Processing and Communications (pp. 1-6). United States: IEEE, Institute of Electrical and Electronics Engineers.
    Chetty, Girija. / Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking. Proceedings of the 2nd International Conference on Signal Processing and Communications. editor / Beata J Wysocki ; Tadeusz A Wysocki. United States : IEEE, Institute of Electrical and Electronics Engineers, 2008. pp. 1-6
    @inproceedings{26bded6ebe114d6cb1843be9b5d229c0,
    title = "Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking",
    abstract = "In this paper we examine two different automated video surveillance techniques for detection and tracking of pedestrians based on fusion of colour and thermal images. The first approach is a novel particle filtering based on Bayesian framework, and the seconf one is an approach based on fusion of shape and appearance cues. The shape and appearance based technique involves a layered two pass scheme, where in the first pass-an expectation-maximization (EM) algorithm is used to separate infrared images into still background and moving foreground layers. In the second pass: shape cues from the first pass is used to eliminate non-pedestrian moving objects and then appearance cue is used to locate the exact position of pedestrians. Then pedestrians are detected by sequential application of templates at multiple scales. For tracking the pedestrian a graph matching-based algorithm which fueses the shape and appearance information was used. The particle filtering based algorithm on other hand is based on building a scene background model with each pixel represented as a multimodal distribution of colour and thermal images. Then this background model is used to build a particle filter for tracking the pedestrian. The particle filter uses a novel formulation of observation likelihoods The evaluation of the two detection and tracking approaches was done by performing experiments on the thermal and colour dataset from OTCBVS database",
    author = "Girija Chetty",
    year = "2008",
    language = "English",
    isbn = "9780975693469",
    pages = "1--6",
    editor = "Wysocki, {Beata J} and Wysocki, {Tadeusz A}",
    booktitle = "Proceedings of the 2nd International Conference on Signal Processing and Communications",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Chetty, G 2008, Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking. in BJ Wysocki & TA Wysocki (eds), Proceedings of the 2nd International Conference on Signal Processing and Communications. IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1-6, 2nd International Conference on Signal Processing and Communications, Gold Coast, Australia, 15/12/08.

    Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking. / Chetty, Girija.

    Proceedings of the 2nd International Conference on Signal Processing and Communications. ed. / Beata J Wysocki; Tadeusz A Wysocki. United States : IEEE, Institute of Electrical and Electronics Engineers, 2008. p. 1-6.

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

    TY - GEN

    T1 - Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking

    AU - Chetty, Girija

    PY - 2008

    Y1 - 2008

    N2 - In this paper we examine two different automated video surveillance techniques for detection and tracking of pedestrians based on fusion of colour and thermal images. The first approach is a novel particle filtering based on Bayesian framework, and the seconf one is an approach based on fusion of shape and appearance cues. The shape and appearance based technique involves a layered two pass scheme, where in the first pass-an expectation-maximization (EM) algorithm is used to separate infrared images into still background and moving foreground layers. In the second pass: shape cues from the first pass is used to eliminate non-pedestrian moving objects and then appearance cue is used to locate the exact position of pedestrians. Then pedestrians are detected by sequential application of templates at multiple scales. For tracking the pedestrian a graph matching-based algorithm which fueses the shape and appearance information was used. The particle filtering based algorithm on other hand is based on building a scene background model with each pixel represented as a multimodal distribution of colour and thermal images. Then this background model is used to build a particle filter for tracking the pedestrian. The particle filter uses a novel formulation of observation likelihoods The evaluation of the two detection and tracking approaches was done by performing experiments on the thermal and colour dataset from OTCBVS database

    AB - In this paper we examine two different automated video surveillance techniques for detection and tracking of pedestrians based on fusion of colour and thermal images. The first approach is a novel particle filtering based on Bayesian framework, and the seconf one is an approach based on fusion of shape and appearance cues. The shape and appearance based technique involves a layered two pass scheme, where in the first pass-an expectation-maximization (EM) algorithm is used to separate infrared images into still background and moving foreground layers. In the second pass: shape cues from the first pass is used to eliminate non-pedestrian moving objects and then appearance cue is used to locate the exact position of pedestrians. Then pedestrians are detected by sequential application of templates at multiple scales. For tracking the pedestrian a graph matching-based algorithm which fueses the shape and appearance information was used. The particle filtering based algorithm on other hand is based on building a scene background model with each pixel represented as a multimodal distribution of colour and thermal images. Then this background model is used to build a particle filter for tracking the pedestrian. The particle filter uses a novel formulation of observation likelihoods The evaluation of the two detection and tracking approaches was done by performing experiments on the thermal and colour dataset from OTCBVS database

    M3 - Conference contribution

    SN - 9780975693469

    SP - 1

    EP - 6

    BT - Proceedings of the 2nd International Conference on Signal Processing and Communications

    A2 - Wysocki, Beata J

    A2 - Wysocki, Tadeusz A

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - United States

    ER -

    Chetty G. Comparative Evaluation of Two Multisensory Video Surveillance Techniques for Pedestrian Tracking. In Wysocki BJ, Wysocki TA, editors, Proceedings of the 2nd International Conference on Signal Processing and Communications. United States: IEEE, Institute of Electrical and Electronics Engineers. 2008. p. 1-6