Study on human gesture recognition from moving camera images

Dan Luo, Jun Ohya

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

    2 Citations (Scopus)

    Abstract

    We develop a framework based approach to extract and recognize hand gestures from the video sequence acquired by a dynamic camera, which could be a useful interface between humans and mobile robots. We use Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face and body part. Hand trajectory motion models (HTMM) are constructed by HFLC and hand blob changing factor. In this paper, we apply a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Each HTMM in the database is classified into gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 51 kinds of sign language based Japanese and American Sign Language gestures obtained from 7 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    Original languageEnglish
    Title of host publication2010 IEEE International Conference on Multimedia and Expo, ICME 2010
    Pages274-279
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event2010 IEEE International Conference on Multimedia and Expo, ICME 2010 - Singapore
    Duration: 2010 Jul 192010 Jul 23

    Other

    Other2010 IEEE International Conference on Multimedia and Expo, ICME 2010
    CitySingapore
    Period10/7/1910/7/23

    Fingerprint

    Gesture recognition
    Principal component analysis
    Cameras
    Trajectories
    Mobile robots
    Condensation
    Experiments

    Keywords

    • Active camera
    • Condensation
    • Hand gesture
    • HFLC
    • PCA

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Software

    Cite this

    Luo, D., & Ohya, J. (2010). Study on human gesture recognition from moving camera images. In 2010 IEEE International Conference on Multimedia and Expo, ICME 2010 (pp. 274-279). [5582998] https://doi.org/10.1109/ICME.2010.5582998

    Study on human gesture recognition from moving camera images. / Luo, Dan; Ohya, Jun.

    2010 IEEE International Conference on Multimedia and Expo, ICME 2010. 2010. p. 274-279 5582998.

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

    Luo, D & Ohya, J 2010, Study on human gesture recognition from moving camera images. in 2010 IEEE International Conference on Multimedia and Expo, ICME 2010., 5582998, pp. 274-279, 2010 IEEE International Conference on Multimedia and Expo, ICME 2010, Singapore, 10/7/19. https://doi.org/10.1109/ICME.2010.5582998
    Luo D, Ohya J. Study on human gesture recognition from moving camera images. In 2010 IEEE International Conference on Multimedia and Expo, ICME 2010. 2010. p. 274-279. 5582998 https://doi.org/10.1109/ICME.2010.5582998
    Luo, Dan ; Ohya, Jun. / Study on human gesture recognition from moving camera images. 2010 IEEE International Conference on Multimedia and Expo, ICME 2010. 2010. pp. 274-279
    @inproceedings{0fc633626568484da34b4a54d7ef3f59,
    title = "Study on human gesture recognition from moving camera images",
    abstract = "We develop a framework based approach to extract and recognize hand gestures from the video sequence acquired by a dynamic camera, which could be a useful interface between humans and mobile robots. We use Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face and body part. Hand trajectory motion models (HTMM) are constructed by HFLC and hand blob changing factor. In this paper, we apply a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Each HTMM in the database is classified into gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 51 kinds of sign language based Japanese and American Sign Language gestures obtained from 7 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.",
    keywords = "Active camera, Condensation, Hand gesture, HFLC, PCA",
    author = "Dan Luo and Jun Ohya",
    year = "2010",
    doi = "10.1109/ICME.2010.5582998",
    language = "English",
    isbn = "9781424474912",
    pages = "274--279",
    booktitle = "2010 IEEE International Conference on Multimedia and Expo, ICME 2010",

    }

    TY - GEN

    T1 - Study on human gesture recognition from moving camera images

    AU - Luo, Dan

    AU - Ohya, Jun

    PY - 2010

    Y1 - 2010

    N2 - We develop a framework based approach to extract and recognize hand gestures from the video sequence acquired by a dynamic camera, which could be a useful interface between humans and mobile robots. We use Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face and body part. Hand trajectory motion models (HTMM) are constructed by HFLC and hand blob changing factor. In this paper, we apply a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Each HTMM in the database is classified into gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 51 kinds of sign language based Japanese and American Sign Language gestures obtained from 7 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    AB - We develop a framework based approach to extract and recognize hand gestures from the video sequence acquired by a dynamic camera, which could be a useful interface between humans and mobile robots. We use Human-Following Local Coordinate (HFLC) System, a very simple and stable method for extracting hand motion trajectories, which is obtained from the located human face and body part. Hand trajectory motion models (HTMM) are constructed by HFLC and hand blob changing factor. In this paper, we apply a principal component analysis (PCA) based approach to improve the recognition accuracy. For further improvement, temporal changes in the observed hand area changing factor are utilized as new image features to be stored in the database after being analyzed by PCA. Each HTMM in the database is classified into gesture categories, or temporal changes in hand blob changes. We demonstrate the effectiveness of the proposed method by conducting experiments on 51 kinds of sign language based Japanese and American Sign Language gestures obtained from 7 people. Our experimental recognition results show better performance is obtained by PCA based approach than the Condensation algorithm based method.

    KW - Active camera

    KW - Condensation

    KW - Hand gesture

    KW - HFLC

    KW - PCA

    UR - http://www.scopus.com/inward/record.url?scp=78349268310&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=78349268310&partnerID=8YFLogxK

    U2 - 10.1109/ICME.2010.5582998

    DO - 10.1109/ICME.2010.5582998

    M3 - Conference contribution

    SN - 9781424474912

    SP - 274

    EP - 279

    BT - 2010 IEEE International Conference on Multimedia and Expo, ICME 2010

    ER -