Deflection measurement is the research focus of health monitoring for bridges during the operation period. This study develops a contactless measurement technique to monitor the bridge deflection, leveraging visual information from a team of unmanned aerial vehicles (UAVs). On the basis of the collinearity of the laser spots projected on the plane by the coplanar laser indicator, we can eliminate the motion of UAV, and calculate the vertical displacement of the position to be measured relative to the bridge pier. In the proposed method, the center of the laser spot is extracted through a method based on deep learning, and an algorithm based on scale-invariant features registration was developed to track the feature points of the bridge in the image sequence. According to the algorithm, we demonstrate the accuracy and feasibility of our approach through simulation and simulated bridge experiments. The result shows that the root mean squared error (RMSE) of measurement through our technique is less than 0.5 mm in the laboratory conditions. In addition, the limits and scalability of the presented method have been explored through a field experiment.

No abstract

No abstract

No abstract

Space exploration missions involve significant participation from astronauts. Therefore, it is of great practical importance to assess the astronauts’ performance via various parameters in the cramped and weightless space station. In this paper, we proposed a calibration-free multi-view vision system for astronaut performance capture, including two modules: (1) an alternating iterative optimization of the camera pose and human pose is implemented to calibrate the extrinsic camera parameters with detected 2D keypoints. (2) Scale factors are restricted by the limb length to recover the real-world scale and the shape parameters are refined for subsequent postural reconstruction. These two modules can provide effective and efficient motion capture in a weightless space station. Extensive experiments using public datasets and the ground verification test data demonstrated the accuracy of the estimated camera pose and the effectiveness of the reconstructed human pose.