Computer Vision Approach to Study Deformation of Materials

TL;DR

This paper explores using computer vision algorithms to analyze material deformation, demonstrating improved accuracy in strain mapping and opening new interdisciplinary research opportunities in mechanics and materials science.

Contribution

The study introduces a novel computer vision approach for deformation analysis, validated through experiments and virtual tests, enhancing accuracy over traditional methods.

Findings

Virtual experiments show improved strain mapping accuracy.

Validated method against extensometer and DIC results.

Potential for new deformation analysis techniques.

Abstract

Characterization of the deformation of materials across different length scales has continuously attracted enormous attention from the mechanics and materials communities. In this study, the possibility of utilizing a computer vision algorithm to extract deformation information of materials has been explored, which greatly expands the use of computer vision approaches to studying mechanics of materials and potentially opens new dialogues between the two communities. The computer vision algorithm is first developed and tested on computationally deformed images, before evaluating experimentally collected images on speckle painted samples before and after deformation. Moreover, a virtual experiment has also shown the feasibility of mapping surface strain of a sample based on its natural pattern with significantly improved accuracy compared to DIC result, which provides new opportunities in experimentation and computer algorithms to study deformation mechanics of materials. Validation experiments include evaluating the performance of strain mapping using the computer vision approach in the uniaxial tensile test and three-point bending test, compared with extensometer reading and digital image correlation respectively.