Quasi-motion extraction utilizing edge field analysis

Mitsuharu Matsumoto, Shuji Hashimoto

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

    1 Citation (Scopus)

    Abstract

    Recognizing the motion in the images is an important part of computer vision. In order to recognize the motion in the images, it is significant to distinguish three motion primitives as translation, rotation and divergence that can be extracted based on the optical flow. In this paper, we introduce a method for extracting quasi-motion utilizing edge flow in one image, namely edge field analysis. In general, the optical flow is estimated utilizing two or more successive images. On the other hand, this method directly estimates translation, rotation and divergence not utilizing two or more images but utilizing only one image without the information of the optical flow of the motion. We firstly formulate the problem of extracting the motion primitives as a vector field analysis of the velocity vector field. We then propose an algorithm for estimating three motion primitives from one image regarding edge as pseudo-velocity vector. The experimental results in terms of estimating the eye of the storm, Whirlpool Galaxy and the center of the explosion are also demonstrated to evaluate the proposed method.

    Original languageEnglish
    Title of host publicationProceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006
    Pages28-33
    Number of pages6
    Publication statusPublished - 2006
    Event8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006 - Honolulu, HI
    Duration: 2006 Aug 142006 Aug 16

    Other

    Other8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006
    CityHonolulu, HI
    Period06/8/1406/8/16

    Fingerprint

    Optical flows
    Galaxies
    Computer vision
    Explosions

    Keywords

    • Edge field analysis
    • Feature extraction
    • Quasi-motion extraction
    • Vector field analysis

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition
    • Signal Processing

    Cite this

    Matsumoto, M., & Hashimoto, S. (2006). Quasi-motion extraction utilizing edge field analysis. In Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006 (pp. 28-33)

    Quasi-motion extraction utilizing edge field analysis. / Matsumoto, Mitsuharu; Hashimoto, Shuji.

    Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. p. 28-33.

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

    Matsumoto, M & Hashimoto, S 2006, Quasi-motion extraction utilizing edge field analysis. in Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. pp. 28-33, 8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006, Honolulu, HI, 06/8/14.
    Matsumoto M, Hashimoto S. Quasi-motion extraction utilizing edge field analysis. In Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. p. 28-33
    Matsumoto, Mitsuharu ; Hashimoto, Shuji. / Quasi-motion extraction utilizing edge field analysis. Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. pp. 28-33
    @inproceedings{afdaadb0ec164707bb5775efec539583,
    title = "Quasi-motion extraction utilizing edge field analysis",
    abstract = "Recognizing the motion in the images is an important part of computer vision. In order to recognize the motion in the images, it is significant to distinguish three motion primitives as translation, rotation and divergence that can be extracted based on the optical flow. In this paper, we introduce a method for extracting quasi-motion utilizing edge flow in one image, namely edge field analysis. In general, the optical flow is estimated utilizing two or more successive images. On the other hand, this method directly estimates translation, rotation and divergence not utilizing two or more images but utilizing only one image without the information of the optical flow of the motion. We firstly formulate the problem of extracting the motion primitives as a vector field analysis of the velocity vector field. We then propose an algorithm for estimating three motion primitives from one image regarding edge as pseudo-velocity vector. The experimental results in terms of estimating the eye of the storm, Whirlpool Galaxy and the center of the explosion are also demonstrated to evaluate the proposed method.",
    keywords = "Edge field analysis, Feature extraction, Quasi-motion extraction, Vector field analysis",
    author = "Mitsuharu Matsumoto and Shuji Hashimoto",
    year = "2006",
    language = "English",
    isbn = "0889865833",
    pages = "28--33",
    booktitle = "Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006",

    }

    TY - GEN

    T1 - Quasi-motion extraction utilizing edge field analysis

    AU - Matsumoto, Mitsuharu

    AU - Hashimoto, Shuji

    PY - 2006

    Y1 - 2006

    N2 - Recognizing the motion in the images is an important part of computer vision. In order to recognize the motion in the images, it is significant to distinguish three motion primitives as translation, rotation and divergence that can be extracted based on the optical flow. In this paper, we introduce a method for extracting quasi-motion utilizing edge flow in one image, namely edge field analysis. In general, the optical flow is estimated utilizing two or more successive images. On the other hand, this method directly estimates translation, rotation and divergence not utilizing two or more images but utilizing only one image without the information of the optical flow of the motion. We firstly formulate the problem of extracting the motion primitives as a vector field analysis of the velocity vector field. We then propose an algorithm for estimating three motion primitives from one image regarding edge as pseudo-velocity vector. The experimental results in terms of estimating the eye of the storm, Whirlpool Galaxy and the center of the explosion are also demonstrated to evaluate the proposed method.

    AB - Recognizing the motion in the images is an important part of computer vision. In order to recognize the motion in the images, it is significant to distinguish three motion primitives as translation, rotation and divergence that can be extracted based on the optical flow. In this paper, we introduce a method for extracting quasi-motion utilizing edge flow in one image, namely edge field analysis. In general, the optical flow is estimated utilizing two or more successive images. On the other hand, this method directly estimates translation, rotation and divergence not utilizing two or more images but utilizing only one image without the information of the optical flow of the motion. We firstly formulate the problem of extracting the motion primitives as a vector field analysis of the velocity vector field. We then propose an algorithm for estimating three motion primitives from one image regarding edge as pseudo-velocity vector. The experimental results in terms of estimating the eye of the storm, Whirlpool Galaxy and the center of the explosion are also demonstrated to evaluate the proposed method.

    KW - Edge field analysis

    KW - Feature extraction

    KW - Quasi-motion extraction

    KW - Vector field analysis

    UR - http://www.scopus.com/inward/record.url?scp=34548203349&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34548203349&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 0889865833

    SN - 9780889865839

    SP - 28

    EP - 33

    BT - Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006

    ER -