ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums

Abstract

We train an object detector built from convolutional neural networks to count interference fringes in elliptical antinode regions in frames of high-speed video recordings of transient oscillations in Caribbean steelpan drums illuminated by electronic speckle pattern interferometry (ESPI). The annotations provided by our model aim to contribute to the understanding of time-dependent behavior in such drums by tracking the development of sympathetic vibration modes. The system is trained on a dataset of crowdsourced human-annotated images obtained from the Zooniverse Steelpan Vibrations Project. Due to the small number of human-annotated images and the ambiguity of the annotation task, we also evaluate the model on a large corpus of synthetic images whose properties have been matched to the real images by style transfer using a Generative Adversarial Network. Applying the model to thousands of unlabeled video frames, we measure oscillations consistent with audio recordings of these drum strikes. One unanticipated result is that sympathetic oscillations of higher-octave notes significantly precede the rise in sound intensity of the corresponding second harmonic tones; the mechanism responsible for this remains unidentified. This paper primarily concerns the development of the predictive model; further exploration of the steelpan images and deeper physical insights await its further application.

arXiv comment13 pages, 9 figures, accepted for J. Acous. Soc. Am. (JASA) Special Issue on Machine Learning in Acoustics

References in corpus (10)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Improved Regularization of Convolutional Neural Networks with Cutout
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Visualizing the Loss Landscape of Neural Nets
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• Three Mechanisms of Weight Decay Regularization
• Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
• Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images

Cited by in corpus (1)

• espiownage: Tracking Transients in Steelpan Drum Strikes Using Surveillance Technology