A non-target structural displacement measurement method using advanced feature matching strategy. Issue 16 (December 2019)

• Record Type: Journal Article
• Authors: Dong, Chuan-Zhi; Catbas, F Necati
• Other Names: Zhou Lu guest-editor.; Ni Yi-Qing guest-editor.
• Is Part Of: Advances in structural engineering. Volume 22:Issue 16(2019)
• Page Start: 3461
• Page End: 3472
• Publication Date: 2019-12
• Subjects: computer vision -- displacement measurement -- feature matching -- learned keypoint descriptors -- structural health monitoring; Structural engineering -- Periodicals; Construction, Technique de la; Structural engineering; Periodicals; 624.1
• DOI: 10.1177/1369433219856171
• Languages: English
• ISSNs: 1369-4332

Abstract

Most of the existing vision-based displacement measurement methods require manual speckles or targets to improve the measurement performance in non-stationary imagery environments. To minimize the use of manual speckles and targets, feature points regarded as virtual markers can be utilized for non-target measurement. In this study, an advanced feature matching strategy is presented, which replaces the handcrafted descriptors with learned descriptors called Visual Geometry Group, of the University of Oxford descriptors to achieve better performance. The feasibility and performance of the proposed method is verified by comparative studies with a laboratory experiment on a two-span bridge model and then with a field application on a railway bridge. The proposed approach of integrated use of Scale Invariant Feature Transform and Visual Geometry Group improved the measurement accuracy by about 24% when compared with the commonly used existing feature matching-based displacement measurement method using Scale Invariant Feature Transform feature and descriptor.