桃園藻礁為海岸重要生態棲地，其範圍易受漂沙覆蓋而改變且位置緊鄰 第三天然氣接收站，因此藻礁辨範圍辨識為重要研究議題。本研究透過監督式 分類法 辨識藻礁 範圍，並將分類結果與人工辨識結果進行準確度評估，藉以檢 視不同分類方法之成效。本研究利用 RGB影像及數值地表模型 影像及數值地表模型 (DSM)兩種資料進行影像分析，別運用三種方法設定訓練樣本的閥值，藉以分類礁體與沙區域。其方法分別為：(1)色彩強度：運用歐幾里得距離計算組成的相色彩強度：運用歐幾里得距離計算組成的相 似程度；(2)影像 梯度：利用灰階影像梯度：利用灰階影像(gray-scale image)在過渡不同區域所產生的在過渡不 同區域所產生的連續性，檢測其梯度變化進行區域劃分；(3)粗糙度粗糙度 (Rugosity)：計算實際地表起 伏的表面積 與正交投影後平面 表面積 的比值 。另將上述三種分類之結果進行交 集，以驗證同時採用多種分析方法是否能提升影像類的準確度。 三種的分類方法中，使用色彩強度進行時其準確約為 0.49左右，無法有效的區分礁體與沙之域；灰階梯度為三種方中較佳類，其準確度可達 0.8左右；粗糙度分類之準確落於0.34-0.71之間，雖能辨識部分礁體區域，但其準確度變化幅較大。此三種方法交集結果之於0.54-0.71之間，雖無法高於灰階梯度準確但優色彩強或粗糙個別分類之結果。

Taoyuan algal reef is an important coastal ecological habitat, and the area of the reef is easily changed by the coverage of drifting sand. Recently, due to the construction of the third liquefied natural gas (LNG), the algal reefs in Taoyuan are at high-risk of being threatened. Therefore, monitoring the variation of algal reef areas is necessary and an important research topic. This study uses supervised classification to identify the area of algal reefs. Besides, we evaluate the accuracy of the classification methods by comparing the consistent areas between methods to the manual identification results.
Specifically, to identify the reef area and compare it with the manual results, we applied three methods using the orthophotograph and numerical surface model (DSM) data to classify images. Three methods were applied in this study are called as: (1)
Color intensity: using the intensity of color composition (RGB) to classify reefs and sand ; ( 2) Image gradient: the threshold value of detection classification through the variation of the grayscale caused by the transition of heterogeneous regions; (3) Rugosity: Calculating the ratio of the surface area of the undulating terrain to the plane after orthogonal projection. In addition, the results of the three classified methods above are intersected to verify whether the compilation of multiple analysis methods can improve the accuracy of image classification or not.
The results show that the color intensity accuracy is 0.49. Compared to other methods, this accuracy value is not as well as other methods for classification. Thereby, the color intensity is not the perfect method to distinguish the reef and sand areas. Whereas, the grayscale method gives the highest accuracy of about 0.8. The accuracy of the rugosity method is range between 0.34-0.71. Although rugosity can identify some parts of reef areas, but the accuracy varied with the mixing areas between reef and sand. Moreover, the accuracy of the intersection of the three classified methods ranges between 0.54-0.71. Even can not be higher than the accuracy of the gray-scale gradient method but better than the color intensity and rugosity method.

書籍
Gonzalez Wood ,數位影像處理 Digital Image Processing ,普林斯頓國際有限公司，民國九十七年。
英文期刊
Brock, J. C., C. W. Wright, I. B. Kuffner, R. Hernandez and P. Thompson (2006). "Airborne lidar sensing of massive stony coral colonies on patch reefs in the northern Florida reef tract." Remote Sensing of Environment 104(1): 31-42.
Chand, S. and B. Bollard (2021). "Multispectral low altitude remote sensing of wild oyster reefs." Global Ecology and Conservation 30: e01810.
Espriella, M. C., V. Lecours, P. C. Frederick, E. V. Camp and B. Wilkinson (2020). "Quantifying intertidal habitat relative coverage in a Florida estuary using UAS imagery and GEOBIA." Remote Sensing 12(4): 677.
Fallati, L., L. Saponari, A. Savini, F. Marchese, C. Corselli and P. Galli (2020). "Multi-Temporal UAV Data and object-based image analysis (OBIA) for estimation of substrate changes in a post-bleaching scenario on a maldivian reef." Remote Sensing 12(13): 2093.
Friedman, A., O. Pizarro, S. B. Williams and M. Johnson-Roberson (2012). "Multi-scale measures of rugosity, slope and aspect from benthic stereo image reconstructions." PloS one 7(12): e50440.
Gauch, J. M. (1999). "Image segmentation and analysis via multiscale gradient watershed hierarchies." IEEE transactions on image processing 8(1): 69-79.
Grohmann, C. H., M. J. Smith and C. Riccomini (2010). "Multiscale analysis of topographic surface roughness in the Midland Valley, Scotland." IEEE Transactions on Geoscience and Remote Sensing 49(4): 1200-1213.
Ivanov, S., N. Gorlushkina and A. Govorov (2018). "The Recognition and Classification of Objects Based on the Modified Distance Metric." Procedia Computer Science 136: 210-217.
Jenness, J. S. (2004). "Calculating landscape surface area from digital elevation models." Wildlife Society Bulletin 32(3): 829-839.
Kalacska, M., O. Lucanus, L. Sousa, T. Vieira and J. P. Arroyo-Mora (2018). "Freshwater fish habitat complexity mapping using above and underwater structure-from-motion photogrammetry." Remote Sensing 10(12): 1912.
Luckhurst, B. and K. Luckhurst (1978). "Analysis of the influence of substrate variables on coral reef fish communities." Marine Biology 49(4): 317-323.
Panda, A., R. B. Pachori and N. D. Sinnappah-Kang (2021). "Classification of chronic myeloid leukemia neutrophils by hyperspectral imaging using Euclidean and Mahalanobis distances." Biomedical Signal Processing and Control 70: 103025.
Shen, T.-W., C.-C. Li, W.-F. Lin, Y.-H. Tseng, W.-F. Wu, S. Wu, Z.-L. Tseng and M.-H. Hsu (2022). "Improving Image Quality Assessment Based on the Combination of the Power Spectrum of Fingerprint Images and Prewitt Filter." Applied Sciences 12(7): 3320.
Ventura, D., A. Bonifazi, M. F. Gravina, A. Belluscio and G. Ardizzone (2018). "Mapping and classification of ecologically sensitive marine habitats using unmanned aerial vehicle (UAV) imagery and object-based image analysis (OBIA)." Remote Sensing 10(9): 1331.
中文期刊
林恩如, 劉正千, 張智華, 鄭依凡 and 柯明勳 (2013). "運用福衛二號高時空分辨率多光譜影像於台灣全島崩塌地判釋與災害分析." 航測及遙測學刊 17(1): 31-51.
徐仟妤 (2017). "第三天然氣接收站 藻礁悲歌."
陳莉, 魏曉萍 and 王泰盛 (2004). "監督式分類方法於遙測影像判釋之研究." 農業工程學報 50(3): 59-70.
臺灣地形研究室 (2020). "地景保育相關新聞." 地景保育通訊(50): 40-45.
網路資料
〔1〕 李倫、雷梓萱、字貴珍、沈靖棠(2021) 關於海洋與珊瑚，應該知道的事 環境資訊中心 取自https://e-info.org.tw/node/231019
〔2〕 海洋保育署 (2021) 藻礁生態系 取自https://www.oca.gov.tw/ch/home.jsp?id=177&parentpath=0,5,173
〔3〕 桃園市政府 自然樂活 海好有你 桃園海岸生態保護白皮書(2017) 取自https://in.ncu.edu.tw/~enviener/white/
〔4〕 許民陽(2012) 臺灣西北海岸的礁體 地質教室第31卷1期64-73頁 取自https://www.sdec.ntpc.edu.tw/epaper/10511/4.htm
〔5〕 國家教育研究院，(2002) 監督式分類 非監督式分類https://terms.naer.edu.tw/detail/1300431/
〔6〕 內政部 國土測繪中心(2022) 無人機系統介紹 https://www.nlsc.gov.tw/cp.aspx?n=13658
〔7〕 經濟部長王美花談第三接收站爭議 逐字稿
https://hackmd.io/@billy3321/r1zwCZQBO