MoDB: Database system for synthesizing human motion

Timothy Edmunds, Shanmugavelayutham Muthukrishnan, Subarna Sadhukhan, Shinjiro Sueda

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

    Abstract

    Enacting and capturing real motion for all potential scenarios is prohibitively expensive; hence, there is a great demand to synthetically generate realistic human motion. However, it is a central challenge in character animation to synthetically generate a large sequence of smooth human motion. We present a novel, database-centric solution to address this challenge. We demonstrate a method of generating long sequences of motion by performing various similarity-based "joins" on a database of captured motion sequences. This demo illustrates our system (MoDB) and showcases the process of encoding captured motion into relational data and generating realistic motion by concatenating sub-sequences of the captured data according to feasibility metrics. The demo features an interactive character that moves towards user-specified targets; the character's motion is generated by relying on the real time performance of the database for indexing and selection of feasible sub-sequences.

    Original languageEnglish (US)
    Title of host publicationProceedings - 21st International Conference on Data Engineering, ICDE 2005
    Pages1131-1132
    Number of pages2
    DOIs
    StatePublished - Dec 12 2005
    Event21st International Conference on Data Engineering, ICDE 2005 - Tokyo, Japan
    Duration: Apr 5 2005Apr 8 2005

    Publication series

    NameProceedings - International Conference on Data Engineering
    ISSN (Print)1084-4627

    Other

    Other21st International Conference on Data Engineering, ICDE 2005
    CountryJapan
    CityTokyo
    Period4/5/054/8/05

    Fingerprint

    Animation

    ASJC Scopus subject areas

    • Software
    • Signal Processing
    • Information Systems

    Cite this

    Edmunds, T., Muthukrishnan, S., Sadhukhan, S., & Sueda, S. (2005). MoDB: Database system for synthesizing human motion. In Proceedings - 21st International Conference on Data Engineering, ICDE 2005 (pp. 1131-1132). (Proceedings - International Conference on Data Engineering). https://doi.org/10.1109/ICDE.2005.89

    MoDB : Database system for synthesizing human motion. / Edmunds, Timothy; Muthukrishnan, Shanmugavelayutham; Sadhukhan, Subarna; Sueda, Shinjiro.

    Proceedings - 21st International Conference on Data Engineering, ICDE 2005. 2005. p. 1131-1132 (Proceedings - International Conference on Data Engineering).

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

    Edmunds, T, Muthukrishnan, S, Sadhukhan, S & Sueda, S 2005, MoDB: Database system for synthesizing human motion. in Proceedings - 21st International Conference on Data Engineering, ICDE 2005. Proceedings - International Conference on Data Engineering, pp. 1131-1132, 21st International Conference on Data Engineering, ICDE 2005, Tokyo, Japan, 4/5/05. https://doi.org/10.1109/ICDE.2005.89
    Edmunds T, Muthukrishnan S, Sadhukhan S, Sueda S. MoDB: Database system for synthesizing human motion. In Proceedings - 21st International Conference on Data Engineering, ICDE 2005. 2005. p. 1131-1132. (Proceedings - International Conference on Data Engineering). https://doi.org/10.1109/ICDE.2005.89
    Edmunds, Timothy ; Muthukrishnan, Shanmugavelayutham ; Sadhukhan, Subarna ; Sueda, Shinjiro. / MoDB : Database system for synthesizing human motion. Proceedings - 21st International Conference on Data Engineering, ICDE 2005. 2005. pp. 1131-1132 (Proceedings - International Conference on Data Engineering).
    @inproceedings{2e3f3f2c52c64761b70b53120a95495a,
    title = "MoDB: Database system for synthesizing human motion",
    abstract = "Enacting and capturing real motion for all potential scenarios is prohibitively expensive; hence, there is a great demand to synthetically generate realistic human motion. However, it is a central challenge in character animation to synthetically generate a large sequence of smooth human motion. We present a novel, database-centric solution to address this challenge. We demonstrate a method of generating long sequences of motion by performing various similarity-based {"}joins{"} on a database of captured motion sequences. This demo illustrates our system (MoDB) and showcases the process of encoding captured motion into relational data and generating realistic motion by concatenating sub-sequences of the captured data according to feasibility metrics. The demo features an interactive character that moves towards user-specified targets; the character's motion is generated by relying on the real time performance of the database for indexing and selection of feasible sub-sequences.",
    author = "Timothy Edmunds and Shanmugavelayutham Muthukrishnan and Subarna Sadhukhan and Shinjiro Sueda",
    year = "2005",
    month = "12",
    day = "12",
    doi = "10.1109/ICDE.2005.89",
    language = "English (US)",
    isbn = "0769522858",
    series = "Proceedings - International Conference on Data Engineering",
    pages = "1131--1132",
    booktitle = "Proceedings - 21st International Conference on Data Engineering, ICDE 2005",

    }

    TY - GEN

    T1 - MoDB

    T2 - Database system for synthesizing human motion

    AU - Edmunds, Timothy

    AU - Muthukrishnan, Shanmugavelayutham

    AU - Sadhukhan, Subarna

    AU - Sueda, Shinjiro

    PY - 2005/12/12

    Y1 - 2005/12/12

    N2 - Enacting and capturing real motion for all potential scenarios is prohibitively expensive; hence, there is a great demand to synthetically generate realistic human motion. However, it is a central challenge in character animation to synthetically generate a large sequence of smooth human motion. We present a novel, database-centric solution to address this challenge. We demonstrate a method of generating long sequences of motion by performing various similarity-based "joins" on a database of captured motion sequences. This demo illustrates our system (MoDB) and showcases the process of encoding captured motion into relational data and generating realistic motion by concatenating sub-sequences of the captured data according to feasibility metrics. The demo features an interactive character that moves towards user-specified targets; the character's motion is generated by relying on the real time performance of the database for indexing and selection of feasible sub-sequences.

    AB - Enacting and capturing real motion for all potential scenarios is prohibitively expensive; hence, there is a great demand to synthetically generate realistic human motion. However, it is a central challenge in character animation to synthetically generate a large sequence of smooth human motion. We present a novel, database-centric solution to address this challenge. We demonstrate a method of generating long sequences of motion by performing various similarity-based "joins" on a database of captured motion sequences. This demo illustrates our system (MoDB) and showcases the process of encoding captured motion into relational data and generating realistic motion by concatenating sub-sequences of the captured data according to feasibility metrics. The demo features an interactive character that moves towards user-specified targets; the character's motion is generated by relying on the real time performance of the database for indexing and selection of feasible sub-sequences.

    UR - http://www.scopus.com/inward/record.url?scp=28444470117&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=28444470117&partnerID=8YFLogxK

    U2 - 10.1109/ICDE.2005.89

    DO - 10.1109/ICDE.2005.89

    M3 - Conference contribution

    AN - SCOPUS:28444470117

    SN - 0769522858

    T3 - Proceedings - International Conference on Data Engineering

    SP - 1131

    EP - 1132

    BT - Proceedings - 21st International Conference on Data Engineering, ICDE 2005

    ER -