Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras

Takayuki Hori, Jun Ohya, Jun Kurumisawa

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

    Abstract

    This paper proposes a method that identifies and tracks a walking human across discontinuous fields of views of multiple cameras for the purpose of video surveillance. A typical video surveillance system has multiple cameras, but there are several spaces within the surveillance area that are not within any of the camera's field of view. Also, there are discontinuities between the fields of views of adjacent cameras. In such a system, humans need to be tracked across discontinuous fields of views of multiple cameras. Our proposed model addresses this issue using the concepts of gait pattern, gait model, and motion signature. Each human's gait pattern is constructed and stored in a database. This gait pattern spans a tensor space that consists of three dimensions: person, image feature, and spatio-temporal data. A human's gait model can be constructed from the gait pattern using the "tensor decomposition based approach" described in this paper. When human(s) appears in one of the camera's field of a view (which is often discontinuous from the other camera's field of views), the human's motion signature is calculated and compared to each person in the database's gait model. The person with the gait model that is most similar to the motion signature is identified as same person. After the person is identified, the person is tracked within the field of view of the camera using the mean-shift algorithm based on color parameters. We conducted two experiments; the first experiment was identifying and tracking humans in a single video sequence, and experiments, the percentage of subjects that were correctly identified and tracked was better than that of two currently widely-used methods, PCA and nearest-neighbor. In the second experiment was the same as the first experiment but consisted of multiple-cameras with discontinuous views. The second experiment (human tracking across discontinuous images), shows the potential validity of the proposed method in a typical surveillance system.

    Original languageEnglish
    Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
    Volume7533
    DOIs
    Publication statusPublished - 2010
    EventComputational Imaging VIII - San Jose, CA
    Duration: 2010 Jan 182010 Jan 19

    Other

    OtherComputational Imaging VIII
    CitySan Jose, CA
    Period10/1/1810/1/19

    Fingerprint

    Tensor Decomposition
    gait
    walking
    Field of View
    Gait
    field of view
    Tensors
    Camera
    Cameras
    cameras
    tensors
    Decomposition
    decomposition
    Person
    surveillance
    Experiment
    Signature
    Video Surveillance
    Experiments
    signatures

    Keywords

    • Computer vision
    • Gait identification
    • Human motion recognition
    • Motion analysis
    • Motion signature
    • Multiple cameras
    • N-mode SVD
    • Tensor decomposition

    ASJC Scopus subject areas

    • Applied Mathematics
    • Computer Science Applications
    • Electrical and Electronic Engineering
    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics

    Cite this

    Hori, T., Ohya, J., & Kurumisawa, J. (2010). Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7533). [75330X] https://doi.org/10.1117/12.838717

    Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras. / Hori, Takayuki; Ohya, Jun; Kurumisawa, Jun.

    Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7533 2010. 75330X.

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

    Hori, T, Ohya, J & Kurumisawa, J 2010, Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 7533, 75330X, Computational Imaging VIII, San Jose, CA, 10/1/18. https://doi.org/10.1117/12.838717
    Hori, Takayuki ; Ohya, Jun ; Kurumisawa, Jun. / Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7533 2010.
    @inproceedings{d24b1f9c823b410491715b62d4279da0,
    title = "Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras",
    abstract = "This paper proposes a method that identifies and tracks a walking human across discontinuous fields of views of multiple cameras for the purpose of video surveillance. A typical video surveillance system has multiple cameras, but there are several spaces within the surveillance area that are not within any of the camera's field of view. Also, there are discontinuities between the fields of views of adjacent cameras. In such a system, humans need to be tracked across discontinuous fields of views of multiple cameras. Our proposed model addresses this issue using the concepts of gait pattern, gait model, and motion signature. Each human's gait pattern is constructed and stored in a database. This gait pattern spans a tensor space that consists of three dimensions: person, image feature, and spatio-temporal data. A human's gait model can be constructed from the gait pattern using the {"}tensor decomposition based approach{"} described in this paper. When human(s) appears in one of the camera's field of a view (which is often discontinuous from the other camera's field of views), the human's motion signature is calculated and compared to each person in the database's gait model. The person with the gait model that is most similar to the motion signature is identified as same person. After the person is identified, the person is tracked within the field of view of the camera using the mean-shift algorithm based on color parameters. We conducted two experiments; the first experiment was identifying and tracking humans in a single video sequence, and experiments, the percentage of subjects that were correctly identified and tracked was better than that of two currently widely-used methods, PCA and nearest-neighbor. In the second experiment was the same as the first experiment but consisted of multiple-cameras with discontinuous views. The second experiment (human tracking across discontinuous images), shows the potential validity of the proposed method in a typical surveillance system.",
    keywords = "Computer vision, Gait identification, Human motion recognition, Motion analysis, Motion signature, Multiple cameras, N-mode SVD, Tensor decomposition",
    author = "Takayuki Hori and Jun Ohya and Jun Kurumisawa",
    year = "2010",
    doi = "10.1117/12.838717",
    language = "English",
    isbn = "9780819479266",
    volume = "7533",
    booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

    }

    TY - GEN

    T1 - Identifying a walking human by a tensor decomposition based approach and tracking the human across discontinuous fields of views of multiple cameras

    AU - Hori, Takayuki

    AU - Ohya, Jun

    AU - Kurumisawa, Jun

    PY - 2010

    Y1 - 2010

    N2 - This paper proposes a method that identifies and tracks a walking human across discontinuous fields of views of multiple cameras for the purpose of video surveillance. A typical video surveillance system has multiple cameras, but there are several spaces within the surveillance area that are not within any of the camera's field of view. Also, there are discontinuities between the fields of views of adjacent cameras. In such a system, humans need to be tracked across discontinuous fields of views of multiple cameras. Our proposed model addresses this issue using the concepts of gait pattern, gait model, and motion signature. Each human's gait pattern is constructed and stored in a database. This gait pattern spans a tensor space that consists of three dimensions: person, image feature, and spatio-temporal data. A human's gait model can be constructed from the gait pattern using the "tensor decomposition based approach" described in this paper. When human(s) appears in one of the camera's field of a view (which is often discontinuous from the other camera's field of views), the human's motion signature is calculated and compared to each person in the database's gait model. The person with the gait model that is most similar to the motion signature is identified as same person. After the person is identified, the person is tracked within the field of view of the camera using the mean-shift algorithm based on color parameters. We conducted two experiments; the first experiment was identifying and tracking humans in a single video sequence, and experiments, the percentage of subjects that were correctly identified and tracked was better than that of two currently widely-used methods, PCA and nearest-neighbor. In the second experiment was the same as the first experiment but consisted of multiple-cameras with discontinuous views. The second experiment (human tracking across discontinuous images), shows the potential validity of the proposed method in a typical surveillance system.

    AB - This paper proposes a method that identifies and tracks a walking human across discontinuous fields of views of multiple cameras for the purpose of video surveillance. A typical video surveillance system has multiple cameras, but there are several spaces within the surveillance area that are not within any of the camera's field of view. Also, there are discontinuities between the fields of views of adjacent cameras. In such a system, humans need to be tracked across discontinuous fields of views of multiple cameras. Our proposed model addresses this issue using the concepts of gait pattern, gait model, and motion signature. Each human's gait pattern is constructed and stored in a database. This gait pattern spans a tensor space that consists of three dimensions: person, image feature, and spatio-temporal data. A human's gait model can be constructed from the gait pattern using the "tensor decomposition based approach" described in this paper. When human(s) appears in one of the camera's field of a view (which is often discontinuous from the other camera's field of views), the human's motion signature is calculated and compared to each person in the database's gait model. The person with the gait model that is most similar to the motion signature is identified as same person. After the person is identified, the person is tracked within the field of view of the camera using the mean-shift algorithm based on color parameters. We conducted two experiments; the first experiment was identifying and tracking humans in a single video sequence, and experiments, the percentage of subjects that were correctly identified and tracked was better than that of two currently widely-used methods, PCA and nearest-neighbor. In the second experiment was the same as the first experiment but consisted of multiple-cameras with discontinuous views. The second experiment (human tracking across discontinuous images), shows the potential validity of the proposed method in a typical surveillance system.

    KW - Computer vision

    KW - Gait identification

    KW - Human motion recognition

    KW - Motion analysis

    KW - Motion signature

    KW - Multiple cameras

    KW - N-mode SVD

    KW - Tensor decomposition

    UR - http://www.scopus.com/inward/record.url?scp=77952082168&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77952082168&partnerID=8YFLogxK

    U2 - 10.1117/12.838717

    DO - 10.1117/12.838717

    M3 - Conference contribution

    SN - 9780819479266

    VL - 7533

    BT - Proceedings of SPIE - The International Society for Optical Engineering

    ER -