Displacement serves as a crucial indicator in the field of structure health monitoring for assessing the condition of civil engineering structures. Computer vision is commonly employed for this purpose due to its cost-effectiveness and convenience. Traditional non-contact computer vision methods, such as optical flow, have been applied to obtain the displacement of bridges. However, real-time monitoring remains challenging due to the computational complexity involved. Therefore, optical flow based on deep learning (referred to as deep optical flow) has gained significant attention. Its main advantage lies in its ability to achieve real-time displacement monitoring, which is of great significance. Furthermore, the accuracy of deep optical flow is comparable to that of traditional optical flow methods for displacement measurement. In this paper, the deep optical flow, RAFT-GOCor, is proposed and applied to extract the displacement of structures, then Bayesian RAFT-GOCor based on Monte Carlo dropout is also presented and applied to analyze the uncertainty of the displacement. The algorithms are verified by laboratory simulated experiments and field bridge loading test. The results indicate that both deep optical flow and uncertainty analysis are feasible methods for measuring structural displacement.