This paper aims to achieve a large bridge structural health monitoring (SHM) efficiently, economically, credibly, and holographically through noncontact remote sensing (NRS). For these purposes, the author proposes a NRS method for collecting the holographic geometric deformation of test bridge, using static image sequences. Specifically, a uniaxial automatic cruise acquisition device was designed to collect static images on bridge elevation under different damage conditions. Considering the strong spatiotemporal correlations of the sequence data, the relationships between six fixed fields of view were identified through the SIFT algorithm. On this basis, the deformation of the bridge structure was obtained by tracking a virtual target using the optical flow algorithm. Finally, the global holographic deformation of the test bridge was derived. The research results show that: The output data of our NRS method are basically consistent with the finite-element prediction (maximum error: 11.11%) and dial gauge measurement (maximum error: 12.12%); the NRS method is highly sensitive to the actual deformation of the bridge structure under different damage conditions, and can capture the deformation in a continuous and accurate manner. The research findings lay a solid basis for structure state interpretation and intelligent damage identification.

In structural deformation monitoring, traditional methods are mainly based on the deformation data measured at several individual points. As a result, only the discrete deformation, not the overall one, can be obtained, which hinders the researcher from a better and all-round understanding on the structural behavior. At the same time, the surrounding area around the measuring structure is usually complicated, which notably escalates the difficulty in accessing the deformation data. In dealing with the said issues, a digital image-based method is proposed for the overall structural deformation monitoring, utilizing the image perspective transformation and edge detection. Due to the limitation on camera sites, the lens is usually not orthogonal to the measuring structure. As a result, the obtained image cannot be used to extract the deformation data directly. Thus, the perspective transformation algorithm is used to obtain the orthogonal projection image of the test beam under the condition of inclined photography, which enables the direct extraction of deformation data from the original image. Meanwhile, edge detection operators are used to detect the edge of structure’s orthogonal projection image, to further characterize the key feature of structural deformation. Using the operator, the complete deformation data of structural edge are obtained by locating and calibrating the edge pixels. Based on the above, a series of load tests has been carried out using a steel–concrete composite beam to validate the proposed method, with the implementation of traditional dial deformation gauges. It has been found that the extracted edge lines have an obvious sawtooth effect due to the illumination environment. The sawtooth effect makes the extracted edge lines slightly fluctuate around the actual contour of the structure. On this end, the fitting method is applied to minimize the fluctuation and obtain the linear approximation of the actual deflection curve. The deformation data obtained by the proposed method have been compared with the one measured by the dial meters, indicating that the measurement error of the proposed method is less than 5%. However, since the overall deformation data are continuously measured by the proposed method, it can better reflect the overall deformation of the structure, and moreover the structural health state, when compared with the traditional “point” measurements.