Footstep detection and classification using distributed microphones

Kazuhiro Nakadai, Yuta Fujii, Shigeki Sugano

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

    2 Citations (Scopus)

    Abstract

    This paper addresses footstep detection and classification with multiple microphones distributed on the floor. We propose to introduce geometrical features such as position and velocity of a sound source for classification which is estimated by amplitude-based localization. It does not require precise inter-microphone time synchronization unlike a conventional microphone array technique. To classify various types of sound events, we introduce four types of features, i.e., time-domain, spectral and Cepstral features in addition to the geometrical features. We constructed a prototype system for footstep detection and classification based on the proposed ideas with eight microphones aligned in a 2-by-4 grid manner. Preliminary classification experiments showed that classification accuracy for four types of sound sources such as a walking footstep, running footstep, handclap, and utterance maintains over 70% even when the signal-to-noise ratio is low, like 0 dB. We also confirmed two advantages with the proposed footstep detection and classification. One is that the proposed features can be applied to classification of other sound sources besides footsteps. The other is that the use of a multichannel approach further improves noise-robustness by selecting the best microphone among the microphones, and providing geometrical information on a sound source.

    Original languageEnglish
    Title of host publicationInternational Workshop on Image Analysis for Multimedia Interactive Services
    DOIs
    Publication statusPublished - 2013
    Event2013 14th International Workshop on Image Analysis for Multimedia Interactive Services, WIAMIS 2013 - Paris
    Duration: 2013 Jul 32013 Jul 5

    Other

    Other2013 14th International Workshop on Image Analysis for Multimedia Interactive Services, WIAMIS 2013
    CityParis
    Period13/7/313/7/5

    Fingerprint

    Microphones
    Acoustic waves
    Signal to noise ratio
    Synchronization
    Experiments

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Software

    Cite this

    Nakadai, K., Fujii, Y., & Sugano, S. (2013). Footstep detection and classification using distributed microphones. In International Workshop on Image Analysis for Multimedia Interactive Services [6616127] https://doi.org/10.1109/WIAMIS.2013.6616127

    Footstep detection and classification using distributed microphones. / Nakadai, Kazuhiro; Fujii, Yuta; Sugano, Shigeki.

    International Workshop on Image Analysis for Multimedia Interactive Services. 2013. 6616127.

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

    Nakadai, K, Fujii, Y & Sugano, S 2013, Footstep detection and classification using distributed microphones. in International Workshop on Image Analysis for Multimedia Interactive Services., 6616127, 2013 14th International Workshop on Image Analysis for Multimedia Interactive Services, WIAMIS 2013, Paris, 13/7/3. https://doi.org/10.1109/WIAMIS.2013.6616127
    Nakadai K, Fujii Y, Sugano S. Footstep detection and classification using distributed microphones. In International Workshop on Image Analysis for Multimedia Interactive Services. 2013. 6616127 https://doi.org/10.1109/WIAMIS.2013.6616127
    Nakadai, Kazuhiro ; Fujii, Yuta ; Sugano, Shigeki. / Footstep detection and classification using distributed microphones. International Workshop on Image Analysis for Multimedia Interactive Services. 2013.
    @inproceedings{f4c0195621a1466594c105b16403f710,
    title = "Footstep detection and classification using distributed microphones",
    abstract = "This paper addresses footstep detection and classification with multiple microphones distributed on the floor. We propose to introduce geometrical features such as position and velocity of a sound source for classification which is estimated by amplitude-based localization. It does not require precise inter-microphone time synchronization unlike a conventional microphone array technique. To classify various types of sound events, we introduce four types of features, i.e., time-domain, spectral and Cepstral features in addition to the geometrical features. We constructed a prototype system for footstep detection and classification based on the proposed ideas with eight microphones aligned in a 2-by-4 grid manner. Preliminary classification experiments showed that classification accuracy for four types of sound sources such as a walking footstep, running footstep, handclap, and utterance maintains over 70{\%} even when the signal-to-noise ratio is low, like 0 dB. We also confirmed two advantages with the proposed footstep detection and classification. One is that the proposed features can be applied to classification of other sound sources besides footsteps. The other is that the use of a multichannel approach further improves noise-robustness by selecting the best microphone among the microphones, and providing geometrical information on a sound source.",
    author = "Kazuhiro Nakadai and Yuta Fujii and Shigeki Sugano",
    year = "2013",
    doi = "10.1109/WIAMIS.2013.6616127",
    language = "English",
    isbn = "9781479908332",
    booktitle = "International Workshop on Image Analysis for Multimedia Interactive Services",

    }

    TY - GEN

    T1 - Footstep detection and classification using distributed microphones

    AU - Nakadai, Kazuhiro

    AU - Fujii, Yuta

    AU - Sugano, Shigeki

    PY - 2013

    Y1 - 2013

    N2 - This paper addresses footstep detection and classification with multiple microphones distributed on the floor. We propose to introduce geometrical features such as position and velocity of a sound source for classification which is estimated by amplitude-based localization. It does not require precise inter-microphone time synchronization unlike a conventional microphone array technique. To classify various types of sound events, we introduce four types of features, i.e., time-domain, spectral and Cepstral features in addition to the geometrical features. We constructed a prototype system for footstep detection and classification based on the proposed ideas with eight microphones aligned in a 2-by-4 grid manner. Preliminary classification experiments showed that classification accuracy for four types of sound sources such as a walking footstep, running footstep, handclap, and utterance maintains over 70% even when the signal-to-noise ratio is low, like 0 dB. We also confirmed two advantages with the proposed footstep detection and classification. One is that the proposed features can be applied to classification of other sound sources besides footsteps. The other is that the use of a multichannel approach further improves noise-robustness by selecting the best microphone among the microphones, and providing geometrical information on a sound source.

    AB - This paper addresses footstep detection and classification with multiple microphones distributed on the floor. We propose to introduce geometrical features such as position and velocity of a sound source for classification which is estimated by amplitude-based localization. It does not require precise inter-microphone time synchronization unlike a conventional microphone array technique. To classify various types of sound events, we introduce four types of features, i.e., time-domain, spectral and Cepstral features in addition to the geometrical features. We constructed a prototype system for footstep detection and classification based on the proposed ideas with eight microphones aligned in a 2-by-4 grid manner. Preliminary classification experiments showed that classification accuracy for four types of sound sources such as a walking footstep, running footstep, handclap, and utterance maintains over 70% even when the signal-to-noise ratio is low, like 0 dB. We also confirmed two advantages with the proposed footstep detection and classification. One is that the proposed features can be applied to classification of other sound sources besides footsteps. The other is that the use of a multichannel approach further improves noise-robustness by selecting the best microphone among the microphones, and providing geometrical information on a sound source.

    UR - http://www.scopus.com/inward/record.url?scp=84887233457&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84887233457&partnerID=8YFLogxK

    U2 - 10.1109/WIAMIS.2013.6616127

    DO - 10.1109/WIAMIS.2013.6616127

    M3 - Conference contribution

    SN - 9781479908332

    BT - International Workshop on Image Analysis for Multimedia Interactive Services

    ER -