Extracting full-field subpixel structural displacements from videos via deep learning
Authors:
- Lele LuanLLLele Luan
- Ming L. WangMWMing L. Wang
- Hao SunHSHao Sun
Preprint
Abstract
This paper develops a deep learning framework based on convolutional neural networks (CNNs) that enable real-time extraction of full-field subpixel structural displacements from videos. In particular, two new CNN architectures are designed and trained on a dataset generated by the phase-based motion extraction method from a single lab-recorded high-speed video of a dynamic structure. As displacement is only reliable in the regions with sufficient texture contrast, the sparsity of motion field induced by the texture mask is considered via the network architecture design and loss function definition. Results show that, with the supervision of full and sparse motion field, the trained network is capable of identifying the pixels with sufficient texture contrast as well as their subpixel motions. The performance of the trained networks is tested on various videos of other structures to extract the full-field motion (e.g., displacement time histories), which indicates that the trained networks have generalizability to accurately extract full-field subtle displacements for pixels with sufficient texture contrast.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Development of video analytics with template matching methods for using camera as sensor and application to highway bridge structural health monitoringJournal of Civil Structural Health Monitoring, 2020
- Image‐based back analysis for tension estimation of suspension bridge hanger cablesStructural Control and Health Monitoring, 2020
- Estimation of full‐field, full‐order experimental modal model of cable vibration from digital video measurements with physics‐guided unsupervised machine learning and computer visionStructural Control and Health Monitoring, 2019
- Advances in Computer Vision-Based Civil Infrastructure Inspection and MonitoringEngineering, 2019
- Review of machine-vision based methodologies for displacement measurement in civil structuresJournal of Civil Structural Health Monitoring, 2017
- Digital Image Correlation with Enhanced Accuracy and Efficiency: A Comparison of Two Subpixel Registration AlgorithmsExperimental Mechanics, 2016
- Vision-based multipoint displacement measurement for structural health monitoringStructural Control and Health Monitoring, 2015
- A Database and Evaluation Methodology for Optical FlowInternational Journal of Computer Vision, 2010
- Detecting bridge dynamics with GPS and triaxial accelerometersEngineering Structures, 2007
- Computation of component image velocity from local phase informationInternational Journal of Computer Vision, 1990