| Summary: | 碩士 === 國立臺灣科技大學 === 營建工程系 === 107 === In this study, the smart single-monitor system is composed by attaching single board computer to normal indoor single-monitor. The smart single-monitor system is used to measure the relative displacement between the building layers by means of image measurement, the parameter between pixel coordinates and real coordinates are obtained by the neural network training correction method. The test shows that the measurement results of this method overestimate the results of the LVDT between 1.2 times and 2 times. After adjusting the data, the results become acceptable except some cases which are influenced by blurred images.
The rotation of installation location or the monitor may cause measurement errors that cannot be ignored. For this reason, this study develops the correction technology of rotation effects and uses 3 angular velocity meters on each axis to get rotational signal. However, the above-mentioned correction of the rotation effect has proved to be theoretically feasible, but the excessive noise of the angular velocity meter is too high to use.
This study intends to combat indoor light-influenced, so adds threshold, edge detection, and Hough transformation technology to design three special image processing techniques. According to the result of experiment, adding Hough transformation method in the image processing is better in combating strong light than other two methods. However, Hough transformation method is also more susceptible to noise and twinkle light in the image. If this problem could be fixed, then the feasibility of this technology will enhance.
Keywords: single board computer, structural health monitoring, image measurement, story drift, angular velocity meter, rotation effect, edge detection, Hough transform
|
|---|
