Human action classification in basketball: A single inertial sensor based framework

Xiangyi Meng, Rui Xu, Xuantong Chen, Lingxiang Zheng, Ao Peng, Hai Lu, Haibin Shi, Biyu Tang, Huiru Zheng

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

    Abstract

    Human Action Recognition is becoming more and more important in many fields, especially in sports. However, conventional algorithm are almost camera-based methods, which make it cumbersome and expensive. As the wearable inertial sensor has developed a lot, in this paper, we present a novel human action classification algorithm using in basketball, based on a single inertial sensor, which is a application of multi-label classification. We performed experiment on real world datasets. The AUPRC, AUROC and confusion matrix of our results demonstrated that our novel basketball motion recognizer have a great performance.

    LanguageEnglish
    Title of host publicationFrontier Computing - Theory, Technologies and Applications FC 2017
    Pages152-161
    Number of pages10
    Volume464
    DOIs
    Publication statusPublished - 19 Apr 2018
    Event6th International Conference on Frontier Computing, FC 2017 - Osaka, Japan
    Duration: 12 Jul 201714 Jul 2017

    Publication series

    NameLecture Notes in Electrical Engineering
    Volume464
    ISSN (Print)1876-1100
    ISSN (Electronic)1876-1119

    Conference

    Conference6th International Conference on Frontier Computing, FC 2017
    CountryJapan
    CityOsaka
    Period12/07/1714/07/17

    Fingerprint

    Sensors
    Sports
    Labels
    Cameras
    Experiments

    Keywords

    • Basketball motion
    • Feature extraction
    • Human action recognition
    • Multi-label classification
    • Single inertial sensor
    • Support vector machine

    Cite this

    Meng, X., Xu, R., Chen, X., Zheng, L., Peng, A., Lu, H., ... Zheng, H. (2018). Human action classification in basketball: A single inertial sensor based framework. In Frontier Computing - Theory, Technologies and Applications FC 2017 (Vol. 464, pp. 152-161). (Lecture Notes in Electrical Engineering; Vol. 464). https://doi.org/10.1007/978-981-10-7398-4_16
    Meng, Xiangyi ; Xu, Rui ; Chen, Xuantong ; Zheng, Lingxiang ; Peng, Ao ; Lu, Hai ; Shi, Haibin ; Tang, Biyu ; Zheng, Huiru. / Human action classification in basketball : A single inertial sensor based framework. Frontier Computing - Theory, Technologies and Applications FC 2017. Vol. 464 2018. pp. 152-161 (Lecture Notes in Electrical Engineering).
    @inproceedings{2505d2fd49134a63a44187d34a4747d7,
    title = "Human action classification in basketball: A single inertial sensor based framework",
    abstract = "Human Action Recognition is becoming more and more important in many fields, especially in sports. However, conventional algorithm are almost camera-based methods, which make it cumbersome and expensive. As the wearable inertial sensor has developed a lot, in this paper, we present a novel human action classification algorithm using in basketball, based on a single inertial sensor, which is a application of multi-label classification. We performed experiment on real world datasets. The AUPRC, AUROC and confusion matrix of our results demonstrated that our novel basketball motion recognizer have a great performance.",
    keywords = "Basketball motion, Feature extraction, Human action recognition, Multi-label classification, Single inertial sensor, Support vector machine",
    author = "Xiangyi Meng and Rui Xu and Xuantong Chen and Lingxiang Zheng and Ao Peng and Hai Lu and Haibin Shi and Biyu Tang and Huiru Zheng",
    year = "2018",
    month = "4",
    day = "19",
    doi = "10.1007/978-981-10-7398-4_16",
    language = "English",
    isbn = "9789811073977",
    volume = "464",
    series = "Lecture Notes in Electrical Engineering",
    pages = "152--161",
    booktitle = "Frontier Computing - Theory, Technologies and Applications FC 2017",

    }

    Meng, X, Xu, R, Chen, X, Zheng, L, Peng, A, Lu, H, Shi, H, Tang, B & Zheng, H 2018, Human action classification in basketball: A single inertial sensor based framework. in Frontier Computing - Theory, Technologies and Applications FC 2017. vol. 464, Lecture Notes in Electrical Engineering, vol. 464, pp. 152-161, 6th International Conference on Frontier Computing, FC 2017, Osaka, Japan, 12/07/17. https://doi.org/10.1007/978-981-10-7398-4_16

    Human action classification in basketball : A single inertial sensor based framework. / Meng, Xiangyi; Xu, Rui; Chen, Xuantong; Zheng, Lingxiang; Peng, Ao; Lu, Hai; Shi, Haibin; Tang, Biyu; Zheng, Huiru.

    Frontier Computing - Theory, Technologies and Applications FC 2017. Vol. 464 2018. p. 152-161 (Lecture Notes in Electrical Engineering; Vol. 464).

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

    TY - GEN

    T1 - Human action classification in basketball

    T2 - A single inertial sensor based framework

    AU - Meng, Xiangyi

    AU - Xu, Rui

    AU - Chen, Xuantong

    AU - Zheng, Lingxiang

    AU - Peng, Ao

    AU - Lu, Hai

    AU - Shi, Haibin

    AU - Tang, Biyu

    AU - Zheng, Huiru

    PY - 2018/4/19

    Y1 - 2018/4/19

    N2 - Human Action Recognition is becoming more and more important in many fields, especially in sports. However, conventional algorithm are almost camera-based methods, which make it cumbersome and expensive. As the wearable inertial sensor has developed a lot, in this paper, we present a novel human action classification algorithm using in basketball, based on a single inertial sensor, which is a application of multi-label classification. We performed experiment on real world datasets. The AUPRC, AUROC and confusion matrix of our results demonstrated that our novel basketball motion recognizer have a great performance.

    AB - Human Action Recognition is becoming more and more important in many fields, especially in sports. However, conventional algorithm are almost camera-based methods, which make it cumbersome and expensive. As the wearable inertial sensor has developed a lot, in this paper, we present a novel human action classification algorithm using in basketball, based on a single inertial sensor, which is a application of multi-label classification. We performed experiment on real world datasets. The AUPRC, AUROC and confusion matrix of our results demonstrated that our novel basketball motion recognizer have a great performance.

    KW - Basketball motion

    KW - Feature extraction

    KW - Human action recognition

    KW - Multi-label classification

    KW - Single inertial sensor

    KW - Support vector machine

    UR - http://www.scopus.com/inward/record.url?scp=85045974311&partnerID=8YFLogxK

    U2 - 10.1007/978-981-10-7398-4_16

    DO - 10.1007/978-981-10-7398-4_16

    M3 - Conference contribution

    SN - 9789811073977

    VL - 464

    T3 - Lecture Notes in Electrical Engineering

    SP - 152

    EP - 161

    BT - Frontier Computing - Theory, Technologies and Applications FC 2017

    ER -

    Meng X, Xu R, Chen X, Zheng L, Peng A, Lu H et al. Human action classification in basketball: A single inertial sensor based framework. In Frontier Computing - Theory, Technologies and Applications FC 2017. Vol. 464. 2018. p. 152-161. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-10-7398-4_16