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.

Despite widespread use in a variety of areas, in-field applications of laser Doppler vibrometers (LDVs) are still somewhat limited due to their inherent sensitivity to vibration of the instrument sensor head itself. Earlier work, briefly reviewed herein, has shown it to be possible to subtract the instrument vibration via a number of means, however, it has been difficult up to now to truly compare the performance of these. This is compounded by the constraint that a frequency domain based approach only holds for stationary vibration signals while, particularly for in-field applications, an approach that is also applicable to transient signals is necessary. This paper therefore describes the development of a novel time domain post-processing based approach for vibrating LDV measurement correction and compares it with the frequency domain counterpart. Results show that, while both techniques offer significant improvements in the corrected LDV signal when compared to a reference accelerometer measurement, the time domain based correction outperforms the frequency domain based method by a factor of eight.

No abstract

No abstract