A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction

Wei Quan, Zhenyuan Xu, Junzo Watada

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Image processing and security surveillance system has more and more widely used in recent society such as bank surveillance and pedestrian tracking. The detection of Region of Interest (RoI) is always been regarded as the most significant in tracking system. One of the algorithm which can be used in RoI detecting is 'Density-Based Spatial Clustering of Application with Noise' (DBSCAN). But because of its structure, the runtime consuming costs too much when handling large spatial dataset. Considering the features of image processing, a mesh-divide and Kalman Filter forecasting method is proposed combing DBSCAN for RoI detection and forecasting of image processing. The DBSCAN can be used in the RoI detection and position forecast at the next frame in surveillance system to decrease the runtime cost and improve the accuracy at the same time.

    Original languageEnglish
    Title of host publicationWorld Automation Congress Proceedings
    PublisherIEEE Computer Society
    Pages191-196
    Number of pages6
    ISBN (Print)9781889335490
    DOIs
    Publication statusPublished - 2014 Oct 24
    Event2014 World Automation Congress, WAC 2014 - Waikoloa
    Duration: 2014 Aug 32014 Aug 7

    Other

    Other2014 World Automation Congress, WAC 2014
    CityWaikoloa
    Period14/8/314/8/7

    Fingerprint

    Image processing
    Kalman filters
    Costs

    ASJC Scopus subject areas

    • Control and Systems Engineering

    Cite this

    Quan, W., Xu, Z., & Watada, J. (2014). A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction. In World Automation Congress Proceedings (pp. 191-196). [6935772] IEEE Computer Society. https://doi.org/10.1109/WAC.2014.6935772

    A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction. / Quan, Wei; Xu, Zhenyuan; Watada, Junzo.

    World Automation Congress Proceedings. IEEE Computer Society, 2014. p. 191-196 6935772.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Quan, W, Xu, Z & Watada, J 2014, A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction. in World Automation Congress Proceedings., 6935772, IEEE Computer Society, pp. 191-196, 2014 World Automation Congress, WAC 2014, Waikoloa, 14/8/3. https://doi.org/10.1109/WAC.2014.6935772
    Quan W, Xu Z, Watada J. A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction. In World Automation Congress Proceedings. IEEE Computer Society. 2014. p. 191-196. 6935772 https://doi.org/10.1109/WAC.2014.6935772
    Quan, Wei ; Xu, Zhenyuan ; Watada, Junzo. / A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction. World Automation Congress Proceedings. IEEE Computer Society, 2014. pp. 191-196
    @inproceedings{639b3aa001b04f7b8c392cc42566ce78,
    title = "A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction",
    abstract = "Image processing and security surveillance system has more and more widely used in recent society such as bank surveillance and pedestrian tracking. The detection of Region of Interest (RoI) is always been regarded as the most significant in tracking system. One of the algorithm which can be used in RoI detecting is 'Density-Based Spatial Clustering of Application with Noise' (DBSCAN). But because of its structure, the runtime consuming costs too much when handling large spatial dataset. Considering the features of image processing, a mesh-divide and Kalman Filter forecasting method is proposed combing DBSCAN for RoI detection and forecasting of image processing. The DBSCAN can be used in the RoI detection and position forecast at the next frame in surveillance system to decrease the runtime cost and improve the accuracy at the same time.",
    author = "Wei Quan and Zhenyuan Xu and Junzo Watada",
    year = "2014",
    month = "10",
    day = "24",
    doi = "10.1109/WAC.2014.6935772",
    language = "English",
    isbn = "9781889335490",
    pages = "191--196",
    booktitle = "World Automation Congress Proceedings",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - A mesh-divide-based region of interest clustering and forecasting in video frames based on the background/foreground construction

    AU - Quan, Wei

    AU - Xu, Zhenyuan

    AU - Watada, Junzo

    PY - 2014/10/24

    Y1 - 2014/10/24

    N2 - Image processing and security surveillance system has more and more widely used in recent society such as bank surveillance and pedestrian tracking. The detection of Region of Interest (RoI) is always been regarded as the most significant in tracking system. One of the algorithm which can be used in RoI detecting is 'Density-Based Spatial Clustering of Application with Noise' (DBSCAN). But because of its structure, the runtime consuming costs too much when handling large spatial dataset. Considering the features of image processing, a mesh-divide and Kalman Filter forecasting method is proposed combing DBSCAN for RoI detection and forecasting of image processing. The DBSCAN can be used in the RoI detection and position forecast at the next frame in surveillance system to decrease the runtime cost and improve the accuracy at the same time.

    AB - Image processing and security surveillance system has more and more widely used in recent society such as bank surveillance and pedestrian tracking. The detection of Region of Interest (RoI) is always been regarded as the most significant in tracking system. One of the algorithm which can be used in RoI detecting is 'Density-Based Spatial Clustering of Application with Noise' (DBSCAN). But because of its structure, the runtime consuming costs too much when handling large spatial dataset. Considering the features of image processing, a mesh-divide and Kalman Filter forecasting method is proposed combing DBSCAN for RoI detection and forecasting of image processing. The DBSCAN can be used in the RoI detection and position forecast at the next frame in surveillance system to decrease the runtime cost and improve the accuracy at the same time.

    UR - http://www.scopus.com/inward/record.url?scp=84908895292&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84908895292&partnerID=8YFLogxK

    U2 - 10.1109/WAC.2014.6935772

    DO - 10.1109/WAC.2014.6935772

    M3 - Conference contribution

    SN - 9781889335490

    SP - 191

    EP - 196

    BT - World Automation Congress Proceedings

    PB - IEEE Computer Society

    ER -