A visual measurement method of structural body vibration displacement combined with image deblurring

Abstract

The visual vibration displacement measurement task is limited by the acquisition equipment or the acquisition environment, and there are still defects in the recognition rate. In this paper, starting from the aspect of enhancing the feature information of the input image, a visual measurement method for structural body vibration displacement is constructed combining deblurring and image feature enhancement. Aiming at problems such as blurring that may be encountered during image data acquisition, this paper designs a Multi-Scale Structural Body Image Deblurring Network (MSDNet) based on the Encoder–Decoder architecture to enhance the target feature details in the structural body image. MSDNet obtains more detailed feature information of the structural body by aggregating feature information at different scales in the Encoder–Decoder architecture. Meanwhile, this paper uses the super-resolution image reconstruction method in the Decoder stage instead of the upsampling method to better preserve the feature information of the underlying image. To verify the effectiveness of the method proposed in this paper, a variety of structural body vibration displacement image datasets were produced, and the sensor simultaneously collected structural body displacement data as standard data. The follow-up experiments can also be concluded that the image data after deblurring processing can have a better measurement accuracy of structural body vibration displacement.