Structural operating deflection shape estimation via a hybrid computer-vision algorithm

Aral Sarrafi; Zhu Mao

doi:10.1117/12.2296784

27 March 2018 Structural operating deflection shape estimation via a hybrid computer-vision algorithm

Aral Sarrafi, Zhu Mao

Proceedings Volume 10600, Health Monitoring of Structural and Biological Systems XII; 106002K (2018) https://doi.org/10.1117/12.2296784
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2018, Denver, Colorado, United States

Abstract

Non-contact optical measurements are being more commonly used in numerous industrial and research domains to obtain reliable displacement measurements, due to their unique advantageous over other instrumentations. Phasebased motion estimation and motion magnification are target-less methods to process the sequence of images captured from vibrating structures. Within this study, a new hybrid computer vision algorithm is proposed to process the motion-magnified sequence of images in an automatic fashion. Particle filter enhanced point-tracking method is employed to track the feature points in the motion-magnified videos and k-means clustering algorithm as an autonomous statistical learning method is utilized for the segmentation of the particles. The performance of the proposed algorithm is investigated on the experimental data acquired from a cantilever beam subject to vibration. By applying the proposed algorithm, human interference and supervision can be decreased dramatically compared to the state of the methods such as canny edge detectors. Therefore, the sensitivity of the structural dynamics identification is improved and the ODS vector estimation procedure can be completed in shorter time.

Citation Download Citation

Aral Sarrafi and Zhu Mao "Structural operating deflection shape estimation via a hybrid computer-vision algorithm", Proc. SPIE 10600, Health Monitoring of Structural and Biological Systems XII, 106002K (27 March 2018); https://doi.org/10.1117/12.2296784

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available