Non-Contact Vibro-Acoustic Object Recognition Using Laser Doppler Vibrometry and Convolutional Neural Networks

被引:4
|
作者
Darwish, Abdel [1 ]
Halkon, Benjamin [1 ]
Oberst, Sebastian [1 ]
机构
[1] Univ Technol Sydney, Ctr Audio Acoust & Vibrat, Ultimo, NSW 2007, Australia
关键词
vibratory response; vibro-acoustic classification; acoustic fingerprint; non-contact excitation; transfer learning; deep learning;
D O I
10.3390/s22239360
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Laser Doppler vibrometers (LDVs) have been widely adopted due to their large number of benefits in comparison to traditional contacting vibration transducers. Their high sensitivity, among other unique characteristics, has also led to their use as optical microphones, where the measurement of object vibration in the vicinity of a sound source can act as a microphone. Recent work enabling full correction of LDV measurement in the presence of sensor head vibration unlocks new potential applications, including integration within autonomous vehicles (AVs). In this paper, the common AV challenge of object classification is addressed by presenting and evaluating a novel, non-contact vibro-acoustic object recognition technique. This technique utilises a custom set-up involving a synchronised loudspeaker and scanning LDV to simultaneously remotely solicit and record responses to a periodic chirp excitation in various objects. The 864 recorded signals per object were pre-processed into spectrograms of various forms, which were used to train a ResNet-18 neural network via transfer learning to accurately recognise the objects based only on their vibro-acoustic characteristics. A five-fold cross-validation optimisation approach is described, through which the effects of data set size and pre-processing type on classification accuracy are assessed. A further assessment of the ability of the CNN to classify never-before-seen objects belonging to groups of similar objects on which it has been trained is then described. In both scenarios, the CNN was able to obtain excellent classification accuracy of over 99.7%. The work described here demonstrates the significant promise of such an approach as a viable non-contact object recognition technique suitable for various machine automation tasks, for example, defect detection in production lines or even loose rock identification in underground mines.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Non-contact measurement of facial actions using laser Doppler vibrometry
    Rohrbaugh, J. W.
    Sirevaag, E. J.
    INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 2012, 85 (03) : 312 - 312
  • [2] Vibro-acoustic analysis of synchronous belts by Laser Doppler vibrometry and Boundary Element techniques
    Di Giacomo, T
    Di Sante, R
    Ferri, G
    Rossi, GL
    Santolini, C
    Tomasini, EP
    FOURTH INTERNATIONAL CONFERENCE ON VIBRATION MEASUREMENTS BY LASER TECHNIQUES: ADVANCES AND APPLICATIONS, 2000, 4072 : 542 - 552
  • [3] Non-contact Vibro-acoustic Detection Technique for Dental Osseointegration Examination
    Zhuang, Han-Bo
    Tu, Wei-Shan
    Pan, Min-Chun
    Wu, Jer-Whey
    Chen, Chin-Sung
    Lee, Shyh-Yuan
    Yang, Yuan-Chao
    JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING, 2013, 33 (01) : 35 - 44
  • [4] Non-contact assessment of facial myographic activity using laser Doppler vibrometry
    Rohrbaugh, JW
    Sirevaag, EJ
    Rice, RR
    Ryan, AH
    PSYCHOPHYSIOLOGY, 2003, 40 : S73 - S73
  • [5] Development of a tool for vibro-acoustic design of timing belts by integration of Laser Doppler Vibrometry and Boundary Element techniques
    Di Sante, R
    Tomasini, EP
    Rossi, GL
    NOISE AND VIBRATION ENGINEERING, VOLS 1 - 3, PROCEEDINGS, 2001, : 1397 - 1404
  • [6] Non-contact rotating beam crack size estimation from vibro-acoustic signals
    Li, C. J.
    Lee, J. H.
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2006, 17 (06) : 1529 - 1536
  • [7] The non-contact measure of the heart rate variability by laser Doppler vibrometry: comparison with electrocardiography
    Cosoli, G.
    Casacanditella, L.
    Tomasini, E. P.
    Scalise, L.
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2016, 27 (06)
  • [8] A Non-Contact Fault Diagnosis Method for Rolling Bearings Based on Acoustic Imaging and Convolutional Neural Networks
    Wang, Ran
    Liu, Fengkai
    Hou, Fatao
    Jiang, Weikang
    Hou, Qilin
    Yu, Longjing
    IEEE ACCESS, 2020, 8 : 132761 - 132774
  • [9] A non-contact inspection method of tile debonding using tuned acoustic wave and laser doppler vibrometer
    Zhao, Yu
    Chen, Yuan
    Ye, Lin
    JOURNAL OF SOUND AND VIBRATION, 2023, 564
  • [10] Face-Free Chest Detection Using Convolutional Neural Networks for Non-Contact Respiration Monitoring
    Anil, Aravind A.
    Karthik, Srinivasa
    Joseph, Jayaraj
    Sivaprakasam, Mohanasankar
    2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,