02/08/2023
By Danielle Fretwell

The Francis College of Engineering, Department of Mechanical Engineering, invites you to attend a doctoral dissertation defense by Nicholas A. Valente on "Computer Vision Techniques for Enhanced Measurement of Subtle Motion."

Candidate Name: Nicholas A. Valente
Degree: Doctoral
Defense Date: Tuesday, Feb. 21, 2023
Time: 8 to 10 a.m. EDT
Location: This will be a virtual defense via Zoom. Those interested in attending should contact the student (nicholas_valente@student.uml.edu) and the committee chair (Zhu_Mao@uml.edu) at least 24 hours prior to the defense to request access to the meeting.

Committee:

  • Advisor Zhu Mao, Ph.D., Associate Professor, Department of Mechanical Engineering, WPI, Affiliate Professor, University of Massachusetts Lowell
  • Christopher Niezrecki, Ph.D., Professor, Department of Mechanical Engineering, University of Massachusetts Lowell
  • Janko Slavič, Ph.D., Professor, Department of Mechanical Engineering, University of Ljubljana
  • Alessandro Sabato, Ph.D., Assistant Professor, Department of Mechanical Engineering, University of Massachusetts Lowell

Brief Abstract:

Phase-based motion magnification (PMM) has been recently investigated in the field of vibration and structural health monitoring for its non-invasive nature to reveal hidden system dynamics. The approach has shown success in magnifying subtle structural oscillatory motions for system identification and observation of operating shapes. Although this method has been implemented and is becoming increasingly popular, the amount of physical motion associated with the degree of magnification has yet to be accurately quantified. Within this work, computer vision techniques are adopted to quantify the relation between amplification and true motion. Motion artifacts distort the integrity of the magnified motion, which can pose problems for accurate quantification.

Within this dissertation, image enhancement and machine learning architecture are implemented to smooth the high-frequency content that is observed following magnification. Following the pre-processing of image data, the use of particle filtering is employed as an efficient way to extract exaggerated motion seen in video. The use of quantification techniques is tested and verified on experimental structures with the use of a high-speed optical sensing system. Also, an investigation into data reduction techniques is conducted to expedite testing in the field setting without having to rely on traditional wired sensing. Ultimately, the results of this dissertation will aid in transitioning PMM from a qualitative evaluation tool to a quantitative measurement tool of subtle displacements.