在颱風及季風引發的異常波浪發生期間，因臺灣東部沿海緩衝帶有限，導致花東海岸公路容易遭受長波衝擊，對往來行人及車輛造成嚴重的危害。為了記錄並同時警戒這些災害事件，交通部運輸研究所已於海岸公路上設置多部攝影機，並於2018年及2021年分別建置臺東及花蓮海岸公路浪襲預警系統，提供浪襲預警資訊，並作為業管單位封路決策之參考依據。
人定勝天路段位於花蓮縣豐濱鄉台11線61K+250至63K+000，為交通部公路總局發布的二級監控浪襲路段，此處因極端氣候所導致的浪襲事件不斷發生，引起國內許多專家、學者及防災機構的關注。交通部運輸研究所亦於2023年利用此處架設的攝影設備建立越波影像判釋技術，提供業管單位浪襲警示資訊及預警系統現場觀測資訊。
本研究參考越波影像判釋技術之成果，發現在波浪較大且下雨情況下，辨識結果將出現非預期的錯誤，表示既有技術存在可精進的空間，並以此為動機建立更能精確捕捉海岸線之影像辨識技術。為了快速取得影像辨識成果同時節省時間成本，程式選擇K-means分群法執行影像分割作業，並搭配L*a*b*色彩空間提高水體分群與非水體分群間的色彩差異性。
為了評估影像辨識技術之成效，辨識結果將以人為辨識為標準進行誤差分析，大部分的數據結果顯示，平均絕對誤差小於2個像素，最大絕對誤差則很少超過20個像素，整體表現皆優於既有技術，可作為精進之替代方案。
透過攝影測量學中的共線方程式，可將影像辨識海岸線之二維影像座標轉換為三維空間座標，藉此獲得颱風誘發之波浪溯升及越波高程。本研究於軒嵐諾颱風(2022)影響期間辨識出大約9公尺的溯升高程，於梅花颱風(2022)影響期間辨識出接近9.5公尺的越波高程，可提供業管單位量化之參考數據。

During the typhoon- and monsoon-induced abnormal waves, the disasters caused by long waves impact coastal highway have frequently occurred in the eastern Taiwan because of limited coastal buffer zone. To make these events traceable, several video cameras have been deployed at the coastal highway by the Institute of Transportation, Ministry of Transportation and Communications.

This study refers to the wave image recognition technology of the Institute of Transportation, Ministry of Transportation and Communications at the "Man Can Conquer Nature" Section of the Provincial Highway No. 11 in Hualien. The goal is to establishes an image recognition technology that can more accurately detect the shoreline. To expedite the research progress, the program selects the K-means clustering algorithm for image segmentation and employs the L*a*b* color space to enhance the color differentiation between water cluster and non-water cluster. By incorporating the collinearity equations from photogrammetry, it becomes possible to obtain elevation of wave runup and overtopping.

1. Aarninkhof, S. G. J., Turner, I. L., Dronkers, T. D. T., Caljouw, M., & Nipius, L. (2003). A video-based technique for mapping intertidal beach bathymetry. Coastal Engineering, 49(4), 275-289.
2. Boak, E. H., & Turner, I. L. (2005). Shoreline definition and detection: a review. Journal of Coastal Research, 21(4), 688-703.
3. Holman, R. A., & Sallenger Jr, A. H. (1986). High-energy nearshore processes. Eos, Transactions American Geophysical Union, 67(49), 1369-1371.
4. Holman, R. A., Sallenger Jr, A. H., Lippmann, T. C., & Haines, J. W. (1993). The application of video image processing to the study of nearshore processes. Oceanography, 6(3), 78-85.
5. Holman, R. A., & Stanley, J. (2007). The history and technical capabilities of Argus. Coastal engineering, 54(6-7), 477-491.
6. Liu, Y. L., & Wu, C. H. (2019). Lifeguarding Operational Camera Kiosk System (LOCKS) for flash rip warning: development and application. Coastal Engineering, 152, 103537.
7. Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129-137.
8. Paravolidakis, V., Ragia, L. C., Moirogiorgou, K., & Zervakis, M. E. (2018). Automatic coastline extraction using edge detection and optimization procedures. Geosciences, 8(11), 407.
9. Perona, P., & Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7), 629-639.
10. Plant, N. G., & Holman, R. A. (1997). Intertidal beach profile estimation using video images. Marine Geology, 140(1-2), 1-24.
11. Plant, N. G., Aarninkhof, S. G. J., Turner, I. L., & Kingston, K. S. (2007). The performance of shoreline detection models applied to video imagery. Journal of Coastal Research, 23(3), 658-670.
12. Quartel, S., Ruessink, B. G., & Kroon, A. (2007). Daily to seasonal cross-shore behaviour of quasi-persistent intertidal beach morphology. Earth Surface Processes and Landforms, 32(9), 1293-1307.
13. Toure, S., Diop, O., Kpalma, K., & Maiga, A. S. (2019). Shoreline detection using optical remote sensing: A review. ISPRS International Journal of Geo-Information, 8(2), 75.
14. Tsiakos, C. A. D., & Chalkias, C. (2023). Use of machine learning and remote sensing techniques for shoreline monitoring: A review of recent literature. Applied Sciences, 13(5), 3268.
15. Turner, I. L., Leyden, V. M., Symonds, G., Mcgrath, J., Jackson, A., Jancar, T., Aarninkhof, S. G. J., & Elshoff, I. (2001) Predicted and observed coastline changes at the Gold Coast artificial reef. Coastal Engineering 2000, 1836–1847.
16. Turner, I. L., Aarninkhof, S. G. J., Dronkers, T. D. T., & Mcgrath, J. (2004). CZM applications of Argus coastal imaging at the Gold Coast, Australia. Journal of Coastal Research, 20(3), 739-752.
17. Uunk, L., Wijnberg, K. M., & Morelissen, R. (2010). Automated mapping of the intertidal beach bathymetry from video images. Coastal Engineering, 57(4), 461-469.
18. Vousdoukas, M. I., Ferreira, P. M., Almeida, L. P., Dodet, G., Psaros, F., Andriolo, U., Taborda, R., Silva A. N., Ruano, A., & Ferreira, O. M. (2011). Performance of intertidal topography video monitoring of a meso-tidal reflective beach in South Portugal. Ocean Dynamics, 61(10), 1521-1540.
19. Wolf, P. R., Dewitt, B. A., & Wilkinson, B. E. (2014). Elements of Photogrammetry with Applications in GIS. McGraw-Hill Education.
20. 交通部運輸研究所(2018)，「海岸公路異常波浪特性及防災應用技術之研究」。
21. 交通部運輸研究所(2021)，「花蓮海岸公路浪襲預警及防災應用技術之研究(1/2)-浪襲預警系統建置」。
22. 交通部運輸研究所(2023)，「應用影像智慧化技術判釋海岸公路及防波堤越波研究(1/4)-日間越波影像判釋」。