The invention relates to the technical field of bridge monitoring, in particular to a bridge displacement monitoring method based on unmanned aerial vehicle
visual identification, which comprises the following steps: S1, generating a flight path covering all key parts of a bridge, and collecting a bridge image by adopting an unmanned aerial vehicle according to the flight path; the method comprises the steps of S1, preprocessing a bridge image, S2, carrying out
feature extraction after the bridge image is preprocessed, S3, carrying out matching on image feature points at different time points, and calculating the displacement of a bridge, S4, carrying out model optimization by adopting a
convolutional neural network to optimize image features, and S5, carrying out hierarchical monitoring on displacement magnitude differences of different components of the bridge, and superposing a displacement calculation result on the bridge image in the form of a thermodynamic diagram or a
vector diagram, and representing the displacement by using a
color gradient. The method adopts the unmanned aerial vehicle
visual identification technology, only needs the unmanned aerial vehicle and the camera, combines the
image processing algorithm and the
deep learning model to calculate the bridge displacement, is high in precision, is low in cost, and is suitable for various types of bridge structures.