Displacement detection method of QR code reference object based on computer vision

In order to realize the concrete quality monitoring, the displacement detection method based on computer vision is adopted by adding the identification label to the concrete specimen. The traditional camera calibration methods often need to make standard checkerboard to calculate the camera parameters. If users use different mobile phones to shoot the same scene, it is impossible to calibrate each mobile camera in advance. Therefore, aiming at the problem that the traditional camera calibration method can't meet the needs of some application scenarios, this paper proposes a method to calibrate the camera by extracting a small number of feature points in the image. Experimental data show that the method can calibrate the camera accurately, and then calculate the reference moving distance according to the basic principle of computer vision, and it has good flexibility.