本研究嘗試採用室內單台監視器搭配單板電腦以影像量測方式測得建築層間相對位移，當中使用了類神經網路訓練校正之方式取得像素座標與真實座標之參數關係，並利用此參數計算出特徵點真實位移，再利用層間位移比比較之概念進行結構損傷程度評估。試驗結果顯示本技術之量測位移結果高估位移計達1.2倍至2倍之間，且兩者存在倍率關係，依倍率進行數據調整後，仍然有高估情況，此乃因地震之震動導致監視器畫面模糊而出現不利於影像量測之情況所造成。
監視器安裝在建築物內之梁、柱、板、牆上，然其安裝點或監視器機構本身旋轉恐造成不可忽視之量測誤差。為此，本研究研發了旋轉效應校正技術，並在監視器三個獨立座標上個別加裝角速度計，透過座標轉換與數值積分得出旋轉效應造成之量測誤差。然上述之旋轉效應校正經實驗驗證證實其理論上可行，但因量測角速度時雜訊過大之緣故，扣除其影響後反而會造成層間位移量測誤差過大，因此必須克服此一雜訊過大之問題後，始有其實務上之可行性。
在光線影響問題上，本研究擬克服一般大樓室內可能干擾影像處理之光線，如較強光照射、光線閃爍和較強光閃爍等情況，進行了三種克服光線影響影像處理技術之設計，採用灰階值二值化處理、邊界偵測、霍夫轉換等演算技術。實驗結果顯示在影像處理中加入霍夫直線轉換之方式有較佳之克服強光照射影響能力，然其也較易受到入光量變化、雜訊、畫面模糊而導致量測位移上出現誤差，若能克服這些問題，將可提升此類克服光線影響影像處理方式之可行性。

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

[1] FEMA (2000). FEMA 355 State of the Art Report on Systems Performance of Steel Moment Frames Subject to Earthquake Ground Shaking, FEMA Washington, DC.
[2] Rathje, E. and M. Crawford (2003). Earthquake damage identification using high-resolution satellite images from the 2003 Northern Algeria earthquake. Workshop on application of remote sensing for disaster response, Irvine, University of California.
[3] Skolnik, D. A. and J. W. Wallace (2010). "Critical assessment of interstory drift measurements." Journal of structural engineering 136(12): 1574-1584.
[4] Yu, Q., et al. (2008). "Experimental behaviour of high performance concrete-filled steel tubular columns." Thin-Walled Structures 46(4): 362-370.
[5] Peters, W. and W. Ranson (1982). "Digital imaging techniques in experimental stress analysis." Optical engineering 21(3): 213427.
[6] Pan, B., et al. (2009). "Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review." Measurement science and technology 20(6): 062001.
[7] Harris, C. and M. Stephens (1988). A combined corner and edge detector. Alvey vision conference, Citeseer.
[8] Fu, G. and A. G. Moosa (2001). "Structural damage diagnosis using high resolution images." Structural Safety 23(4): 281-295.
[9] Wahbeh, A. M., et al. (2003). "A vision-based approach for the direct measurement of displacements in vibrating systems." Smart materials and structures 12(5): 785.
[10] Li, H., et al. (2012). "Relative displacement sensing techniques for postevent structural damage assessment." Journal of structural engineering 139(9): 1421-1434.
[11] Pang, C., et al. (2012). "A flexible and highly sensitive strain-gauge sensor using reversible interlocking of nanofibres." Nature materials 11(9): 795.
[12] Sung, S., et al. (2014). "Feasibility study on an angular velocity-based damage detection method using gyroscopes." Measurement science and technology 25(7): 075009.
[13] Feng, D. and M. Q. Feng (2016). "Vision‐based multipoint displacement measurement for structural health monitoring." Structural Control and Health Monitoring 23(5): 876-890.
[14] Lee, J., et al. (2017). "Computer vision-based structural displacement measurement robust to light-induced image degradation for in-service bridges." Sensors 17(10): 2317.
[15] Gupta, S. and S. G. Mazumdar (2013). "Sobel edge detection algorithm." International journal of computer science and management Research 2(2): 1578-1583.
[16] Canny, J. (1986). "A computational approach to edge detection." IEEE Transactions on pattern analysis and machine intelligence(6): 679-698.