Image processing and behavior planning for robot-rat interaction

Qing Shi, Hiroyuki Ishii, Shinichiro Konno, Shinichi Kinoshita, Atsuo Takanishi

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

    10 Citations (Scopus)

    Abstract

    In this paper, we proposed an automated video processing system to replace the traditional manual annotation, and to improve the adaptivity of the rat-like robot to autonomously interact with rats. The feature parameters of rats, such as body length, body area, circularity, body bend angle, locomotion speed, etc., are extracted based on image processing. These parameters are integrated as the input feature vector of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification methods respectively. Preliminary experiments reveal that the rearing, grooming and rotating actions could be recognized with extremely high rate (more than 90% by SVM and more than 80% by ANN). Furthermore, SVM needs less training computational cost than ANN. Therefore, SVM is superior to ANN for the behavior recognition of rats. By using the SVM-based recognition system, the behavior of the robot is generated adaptive to the rat behavior for different interactions.

    Original languageEnglish
    Title of host publicationProceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
    Pages967-973
    Number of pages7
    DOIs
    Publication statusPublished - 2012
    Event2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012 - Rome
    Duration: 2012 Jun 242012 Jun 27

    Other

    Other2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012
    CityRome
    Period12/6/2412/6/27

    Fingerprint

    Support vector machines
    Rats
    Image processing
    Robots
    Planning
    Neural networks
    Processing
    Costs
    Experiments

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Biomedical Engineering
    • Mechanical Engineering

    Cite this

    Shi, Q., Ishii, H., Konno, S., Kinoshita, S., & Takanishi, A. (2012). Image processing and behavior planning for robot-rat interaction. In Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics (pp. 967-973). [6290292] https://doi.org/10.1109/BioRob.2012.6290292

    Image processing and behavior planning for robot-rat interaction. / Shi, Qing; Ishii, Hiroyuki; Konno, Shinichiro; Kinoshita, Shinichi; Takanishi, Atsuo.

    Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. p. 967-973 6290292.

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

    Shi, Q, Ishii, H, Konno, S, Kinoshita, S & Takanishi, A 2012, Image processing and behavior planning for robot-rat interaction. in Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics., 6290292, pp. 967-973, 2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012, Rome, 12/6/24. https://doi.org/10.1109/BioRob.2012.6290292
    Shi Q, Ishii H, Konno S, Kinoshita S, Takanishi A. Image processing and behavior planning for robot-rat interaction. In Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. p. 967-973. 6290292 https://doi.org/10.1109/BioRob.2012.6290292
    Shi, Qing ; Ishii, Hiroyuki ; Konno, Shinichiro ; Kinoshita, Shinichi ; Takanishi, Atsuo. / Image processing and behavior planning for robot-rat interaction. Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. pp. 967-973
    @inproceedings{88fcf22302c34608a84879739b4d4b19,
    title = "Image processing and behavior planning for robot-rat interaction",
    abstract = "In this paper, we proposed an automated video processing system to replace the traditional manual annotation, and to improve the adaptivity of the rat-like robot to autonomously interact with rats. The feature parameters of rats, such as body length, body area, circularity, body bend angle, locomotion speed, etc., are extracted based on image processing. These parameters are integrated as the input feature vector of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification methods respectively. Preliminary experiments reveal that the rearing, grooming and rotating actions could be recognized with extremely high rate (more than 90{\%} by SVM and more than 80{\%} by ANN). Furthermore, SVM needs less training computational cost than ANN. Therefore, SVM is superior to ANN for the behavior recognition of rats. By using the SVM-based recognition system, the behavior of the robot is generated adaptive to the rat behavior for different interactions.",
    author = "Qing Shi and Hiroyuki Ishii and Shinichiro Konno and Shinichi Kinoshita and Atsuo Takanishi",
    year = "2012",
    doi = "10.1109/BioRob.2012.6290292",
    language = "English",
    isbn = "9781457711992",
    pages = "967--973",
    booktitle = "Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics",

    }

    TY - GEN

    T1 - Image processing and behavior planning for robot-rat interaction

    AU - Shi, Qing

    AU - Ishii, Hiroyuki

    AU - Konno, Shinichiro

    AU - Kinoshita, Shinichi

    AU - Takanishi, Atsuo

    PY - 2012

    Y1 - 2012

    N2 - In this paper, we proposed an automated video processing system to replace the traditional manual annotation, and to improve the adaptivity of the rat-like robot to autonomously interact with rats. The feature parameters of rats, such as body length, body area, circularity, body bend angle, locomotion speed, etc., are extracted based on image processing. These parameters are integrated as the input feature vector of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification methods respectively. Preliminary experiments reveal that the rearing, grooming and rotating actions could be recognized with extremely high rate (more than 90% by SVM and more than 80% by ANN). Furthermore, SVM needs less training computational cost than ANN. Therefore, SVM is superior to ANN for the behavior recognition of rats. By using the SVM-based recognition system, the behavior of the robot is generated adaptive to the rat behavior for different interactions.

    AB - In this paper, we proposed an automated video processing system to replace the traditional manual annotation, and to improve the adaptivity of the rat-like robot to autonomously interact with rats. The feature parameters of rats, such as body length, body area, circularity, body bend angle, locomotion speed, etc., are extracted based on image processing. These parameters are integrated as the input feature vector of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification methods respectively. Preliminary experiments reveal that the rearing, grooming and rotating actions could be recognized with extremely high rate (more than 90% by SVM and more than 80% by ANN). Furthermore, SVM needs less training computational cost than ANN. Therefore, SVM is superior to ANN for the behavior recognition of rats. By using the SVM-based recognition system, the behavior of the robot is generated adaptive to the rat behavior for different interactions.

    UR - http://www.scopus.com/inward/record.url?scp=84867421399&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84867421399&partnerID=8YFLogxK

    U2 - 10.1109/BioRob.2012.6290292

    DO - 10.1109/BioRob.2012.6290292

    M3 - Conference contribution

    SN - 9781457711992

    SP - 967

    EP - 973

    BT - Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics

    ER -