espiownage: Tracking Transients in Steelpan Drum Strikes Using Surveillance Technology

TL;DR

This paper enhances the tracking of transient features in high-speed videos of steelpan drums using ESPI by integrating advanced computer vision techniques and dataset cleaning, achieving better accuracy and faster workflow.

Contribution

It introduces a segmentation-regression map for the entire drum surface and accelerates the data cleaning and training process for rapid development.

Findings

Improved metric scores by 10% or more.

Segmentation-regression map yields comparable fringe counts to object detection.

Workflow enables project completion within 18 days.

Abstract

We present an improvement in the ability to meaningfully track features in high speed videos of Caribbean steelpan drums illuminated by Electronic Speckle Pattern Interferometry (ESPI). This is achieved through the use of up-to-date computer vision libraries for object detection and image segmentation as well as a significant effort toward cleaning the dataset previously used to train systems for this application. Besides improvements on previous metric scores by 10% or more, noteworthy in this project are the introduction of a segmentation-regression map for the entire drum surface yielding interference fringe counts comparable to those obtained via object detection, as well as the accelerated workflow for coordinating the data-cleaning-and-model-training feedback loop for rapid iteration allowing this project to be conducted on a timescale of only 18 days.