Justin G. Chen

Research Affiliate
Civil and Environmental Engineering at MIT
Laboratory for Infrastructure Science and Sustainability

e-mail: ju21743 at mit dot edu or justgchen at gmail dot com

Me

About Me

I am currently a technical staff member at MIT Lincoln Laboratory in the Advanced Capabilities and Technologies group. I have research interests in novel sensor systems, specifically computer vision systems for quantitative measurement of motion and laser vibrometers. I work on applying using these novel sensor systems in combination with machine learning for anomaly detection for structural health monitoring and non-destructive testing. I was a post-doctoral associate in the Department of Civil and Environmental Engineering at MIT in Prof. Oral Buyukozturk's LISS group. I worked closely with Prof. Bill Freeman's and Prof. Fredo Durand's groups in CSAIL. I received my Ph.D in Structures and Materials from the Department of Civil and Environmental Engineering at MIT in 2016, an S.M. in Civil and Environmental Engineering from MIT in 2013, and a B.S. in Physics from Caltech in 2009.

Resume (pdf)
Academic CV (pdf)
Linkedin

Research

Video Camera-based Vibration Measurement

For my doctoral thesis, I worked on developing methods for processing video camera data to make displacement measurements of structures for the purpose of identifying potential damage in civil infrastructure. As a starting point, the Motion Magnification algorithm can magnify small motions in videos in specific bands of frequencies; for structures if you choose the frequencies to coincide with resonant frequencies you can create videos of the approximate or operational mode shapes. Expanding on this, using phase based optical flow, quantitative displacements can be measured from videos and mode shapes can be identified.

Currently, in pseudo real-time we can take a video of a small structure, identify and measure its operational mode shapes, and generate motion magnified video at the identified resonant frequencies. Vibrational inspection of small structures and machinery is currently being developed.

The title of my doctoral thesis was "Video Camera-based Vibration Measurement of Infrastructure".

Pipe

Screenshots from a video of a motion magnified pipe. From left to right: Source, 480 Hz, 1200 Hz, 2400 Hz.

Video Magnification page

Research Sponsor: Shell through the MIT Energy Initiative

Acoustic-Laser Vibrometry

For my Master's thesis I worked on acoustic-laser vibrometry, a technique that uses an acoustic source to excite an object and a laser vibrometer to measure its vibrational response. Specifically, I investigated it to find interfacial defects in FRP-reinforced concrete, characterized the effect of several experimental parameters on the detection performance (distance, acoustic sound level, angle of incidence, dwell time), and provided a method for identifying the aspect ratio of defects.

Master's thesis: Detection of defects in FRP-reinforced concrete with the acoustic-laser vibrometry method

Acoustic-Laser Vibrometry

Diagram of the Acoustic-Laser Vibrometry method

Research Sponsor: NSF and the American Society for Non-destructive Testing

Publications

Refereed Journal and Conference Publications

Conference Proceedings

Publicity

MIT News - 8/2/2016 - Reach in and touch objects in videos with "Interactive Dynamic Video"

ENR - 12/3/2015 - High-Speed Video System Tested for Structure Monitoring

MIT News - 8/27/2015 - Observing invisible vibrations

MIT News - 5/21/2015 - Gauging materials' physical properties from video

The Wall Street Journal - 5/15/2015 - Monitoring Tiny Vibrations to Avert Big Problems

MIT News - 4/23/2015 - Magnifying vibrations in bridges and buildings (youtube video)

Misc.

I autocross with Renegade Miata, Boston BMWCCA, NER SCCA, NCR PCA, and many other clubs at Autocross Moore Army Airfield in Ayer, MA. I instruct and assist with course design at Renegade Miata, BMWCCA, NER PCA, and NCR PCA. I am also a member of the amateur motorsports team PROJECT.Devens.

S2000 Sportcross