A new technique from Massachusetts Institute of Technology researchers estimates material properties of physical objects, such as stiffness and weight, from video.

The method could have application in the field of nondestructive testing, determining materials’ physical properties without extracting samples from them or subjecting them to damaging physical tests. Structural defects, for example, could be found in an airplane’s wing by analyzing video of its vibration during flight.

A given object’s preferred frequencies, and the varying strength of its vibrations at those frequencies, produce a unique pattern, which a variation on the visual-microphone algorithm was able to extract.

The MIT researchers then used machine learning to find correlations between those vibrational patterns and measurements of the objects’ material properties. The correlations they found provided estimates of the elasticity of the bars and of the stiffness and weight per unit area of the analyzed fabrics.

Moreover, aberrations or discontinuities in an object’s typical vibrational patterns could indicate a defect in its structure.


Also: Read a Q&A with a NASA Lead Non-Destructive Evaluation Engineer.