People detection in low-resolution video with non-stationary background

Jianguo Zhang, Shaogang Gong

    Research output: Contribution to journalArticle

    10 Citations (Scopus)

    Abstract

    In this paper, we present a framework for robust people detection in low resolution image sequences of highly cluttered dynamic scenes with non-stationary background. Our model utilizes appearance features together with short- and long-term motion information. In particular, we boost Integral Gradient Orientation histograms of appearance and short-term motion. Outputs from the detector are maintained by a tracker to correct any misdetections. A Bayesian model is then deployed to further fuse long-term motion information based on correlation. Experiments show that our model is more robust with better detection rate compared to the model of Viola et al. [Michael J. Jones Paul Viola, Daniel Snow, Detecting pedestrians using patterns of motion and appearance, International Journal of Computer Vision 63(2) (2005) 153–161].
    Original languageEnglish
    Pages (from-to)437-443
    Number of pages7
    JournalImage and Vision Computing
    Volume27
    Issue number4
    DOIs
    Publication statusPublished - 2009

    Fingerprint

    Electric fuses
    Image resolution
    Snow
    Computer vision
    Detectors
    Experiments

    Cite this

    @article{95fe9ad95f354359b56f22092bc355a2,
    title = "People detection in low-resolution video with non-stationary background",
    abstract = "In this paper, we present a framework for robust people detection in low resolution image sequences of highly cluttered dynamic scenes with non-stationary background. Our model utilizes appearance features together with short- and long-term motion information. In particular, we boost Integral Gradient Orientation histograms of appearance and short-term motion. Outputs from the detector are maintained by a tracker to correct any misdetections. A Bayesian model is then deployed to further fuse long-term motion information based on correlation. Experiments show that our model is more robust with better detection rate compared to the model of Viola et al. [Michael J. Jones Paul Viola, Daniel Snow, Detecting pedestrians using patterns of motion and appearance, International Journal of Computer Vision 63(2) (2005) 153–161].",
    author = "Jianguo Zhang and Shaogang Gong",
    year = "2009",
    doi = "10.1016/j.imavis.2008.06.013",
    language = "English",
    volume = "27",
    pages = "437--443",
    journal = "Image and Vision Computing",
    issn = "0262-8856",
    publisher = "Elsevier",
    number = "4",

    }

    People detection in low-resolution video with non-stationary background. / Zhang, Jianguo; Gong, Shaogang.

    In: Image and Vision Computing, Vol. 27, No. 4, 2009, p. 437-443.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - People detection in low-resolution video with non-stationary background

    AU - Zhang, Jianguo

    AU - Gong, Shaogang

    PY - 2009

    Y1 - 2009

    N2 - In this paper, we present a framework for robust people detection in low resolution image sequences of highly cluttered dynamic scenes with non-stationary background. Our model utilizes appearance features together with short- and long-term motion information. In particular, we boost Integral Gradient Orientation histograms of appearance and short-term motion. Outputs from the detector are maintained by a tracker to correct any misdetections. A Bayesian model is then deployed to further fuse long-term motion information based on correlation. Experiments show that our model is more robust with better detection rate compared to the model of Viola et al. [Michael J. Jones Paul Viola, Daniel Snow, Detecting pedestrians using patterns of motion and appearance, International Journal of Computer Vision 63(2) (2005) 153–161].

    AB - In this paper, we present a framework for robust people detection in low resolution image sequences of highly cluttered dynamic scenes with non-stationary background. Our model utilizes appearance features together with short- and long-term motion information. In particular, we boost Integral Gradient Orientation histograms of appearance and short-term motion. Outputs from the detector are maintained by a tracker to correct any misdetections. A Bayesian model is then deployed to further fuse long-term motion information based on correlation. Experiments show that our model is more robust with better detection rate compared to the model of Viola et al. [Michael J. Jones Paul Viola, Daniel Snow, Detecting pedestrians using patterns of motion and appearance, International Journal of Computer Vision 63(2) (2005) 153–161].

    UR - http://www.scopus.com/inward/record.url?scp=57949114980&partnerID=8YFLogxK

    U2 - 10.1016/j.imavis.2008.06.013

    DO - 10.1016/j.imavis.2008.06.013

    M3 - Article

    VL - 27

    SP - 437

    EP - 443

    JO - Image and Vision Computing

    JF - Image and Vision Computing

    SN - 0262-8856

    IS - 4

    ER -