Visual tracking of multiple targets by multi-Bernoulli filtering of background subtracted image data

R. Hoseinnezhad, Ba-Ngu Vo, T.N. Vu

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    7 Citations (Scopus)

    Abstract

    Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates directly on the image observations and does not require any detection nor training patterns. Instead, we use the recent history of image data for non-parametric background subtraction and apply an efficient multi-target filtering technique, known as the multi-Bernoulli filter, on the resulting grey scale image data. In our experiments, we applied our method to track multiple people in three video sequences from the CAVIAR dataset. The results show that our method can automatically track multiple interacting targets and quickly finds targets entering or leaving the scene.
    Original languageEnglish
    Title of host publicationAdvances in Swarm Intelligence
    Place of PublicationGermany
    PublisherSpringer
    Pages509-518
    ISBN (Electronic)9783642215247
    ISBN (Print)9783642215230
    DOIs
    Publication statusPublished - 2011
    Event2nd International Conference on Swarm Intelligence - Chongqing, China
    Duration: 12 Jun 201115 Jun 2011

    Conference

    Conference2nd International Conference on Swarm Intelligence
    Abbreviated titleICSI 2011
    Country/TerritoryChina
    CityChongqing
    Period12/06/1115/06/11

    Fingerprint

    Dive into the research topics of 'Visual tracking of multiple targets by multi-Bernoulli filtering of background subtracted image data'. Together they form a unique fingerprint.

    Cite this