LiDAR數值高程模型（Digital Elevation Model, DEM）具有穿透植被的特性，反映出精細的地表紋理特徵，本研究希望透過不同岩性在地形上紋理之差異，進行岩性分類，輔助山區地質調查時劃定岩性界線。本研究選擇南橫公路向陽至嘉寶約70平方公里地區作為研究區域，應用範圍內高精度LiDAR-DEM作為研究材料，並利用其衍生之紋理資訊進行岩性分類並與相關地質調查資料進行比對。
　　進行地形紋理分析之前需要先決定分析的空間尺度，故利用半變異元分析，來瞭解地形紋理間具相關性的空間大小，再透過灰階共生矩陣（Gray Level Co-occurrence Matrix, GLCM）的七種紋理特徵(平均值、方差、同質性、對比度、差異性、熵及相關性)，統計地形紋理特性作為分類指標。參照初步地質調查與前人研究資料在三種主要的岩性單元(片岩區、變質火成岩區及板岩區)範圍選定樣本區，將上述紋理特徵以監督式分類法的最大概似分類法（Maximum Likelihood Classifier, MLC）與類神經網路分類法(Neural net Classifier)進行分類，將分類結果比對前人文獻中具有細部地質調查成果之整合岩性圖，估計紋理分類結果的準確度。研究成果中最大概似法分類準確度分別為：片岩區59%；變質火成岩區33%；板岩區45%，整體準確度為48%；類神經網路法分類準確度分別為：片岩區68%；板岩區52%，整體準確度為50%。兩分類法結果在片岩區與板岩區均具有明顯交界，且兩岩性界線空間分布與前人現地調查地質圖大致相符。
　　依據本研究所得到之成果，此工作方法可適用於地質資訊不明確地區，協助初步判釋地質界線的分布趨勢，提供調查工作進行時作為岩性界線分布之參考依據。並且，在地質調查工作進行時可同步將調查所得之資訊重複進行修正，或者是依據欲調查岩性的特性加入如多光譜等其他影像判釋方法，可大幅增加對於未知區域岩性界線劃定的合理性與準確性。

The LiDAR-derived Digital Elevation Model (DEM) is known for its ability of penetrating vegetation canopy and reflecting fine ground surface texture. This study aims to classify lithologies by the difference of texture from the topography, and to assist in delineating the lithological boundaries for geological surveys in mountainous areas. In this study, a 70 km2 area that lies between Xiangyang and Jiabao on the Southern Cross Highway was selected as the study area, and a high-precision LiDAR-derived DEM was applied as the study material. The texture information derived therefrom, on the other hand, was used to classify lithologies and compared with the relevant geological survey data.
Semi-variograms is used to identify the scale of spatial correlation of texture pattern and then, through the seven texture features of Gray Level Co-occurrence Matrix (GLCM), collect statistics on the terrain textures as classification indicators. Next, based on the preliminary geological surveys and previous research of the study area, the training areas were selected from three major lithological units (schist zone, metamagmatic zone and slate zone) for Supervised Classification: Maximum Likelihood Classifier (MLC) and Neural Net Classifier (NNC). The results of both classification methods have shown a clear junction between schist and slate zones. Which is generally consistent with geological maps of literature.

李春生 (1989) 第九條路線:南橫公路沿線地質簡介(中段:梅山山莊至啞口山山莊)，臺灣中部十條地質實習考察路線沿線地質簡介，臺灣地質野外實習指導手冊(二)，臺灣師範大學地科系，第179-209頁。
何春蓀 (1986) 臺灣地質概論:臺灣地質圖說明書。經濟部中央地質調查所，共164頁。
吳曉明 (1996) 臺灣南部橫貫公路埡口至初來地區之岩石組織度及地質構造研究，國立臺灣大學地質研究所，碩士論文，共101頁。
林啟文 (2004) 臺東縣利稻村附近的褶皺構造，地質，第23卷，第4期，第17-28頁。
林榮章 (1999) 都會區多解像力遙測影像之紋理分析，國立中興大學土木工程學系，碩士論文，共71頁。
郭永隆 (1994) 多尺度的紋路分類及分割系統，國立成功大學資訊工程研究所，碩士論文。
陳其瑞 (1984) 臺東縣向陽雲母礦物成因之初步研究，經濟部中央地質調查所特刊，第三號，第161-169頁。
陳家齊、陳惠芬、方建能、楊志豪 (2014) 向陽雲母礦床之礦物組成與成因，臺灣鑛冶，第66卷第4期: 1-10頁。
康金瑋 (2008) 福衛二號衛星影像紋理分析之地質製圖應用-以和平地區為例，國立成功大學地球科學研究所，碩士論文，共98頁。
費立沅、陳勉銘 (2013) 易淹水地區上游集水區地質調查及資料庫建置。經濟部中央地質調查所，共192頁。
經濟部中央地質調查所 (2000) 臺灣地質圖，經濟部中央地質調查所。
劉彥錚 (2013) 應用多重特徵於提升材質辨識的準確性，國立交通大學電控工程研究所，碩士論文，共53頁。
關山及指定地區初步地質調查成果說明書 (2011) 易淹水地區上游集水區地質調查及資料庫建置（第3 期100 年度）集水區地質調查及山崩土石流調查與發生潛勢評估計畫(1/3)，經濟部中央地質調查所，共143頁。
羅百喬、潘立慈、羅偉、李紫彤、陳玟玲、王泰典、謝有忠 (2021) 板岩片岩交界帶附近邊坡穩定與岩體工程特性探討～以南橫公路摩天下馬沿線為例，地工技術，第167卷，第19-28頁。
Alrababah , M. A., Alhamad, M. N. (2006). Land use/cover classification of arid and semi‐arid Mediterranean landscapes using Landsat ETM. International Journal of Remote Sensing. 27:13, 2703–2718. DOI: 10.1080/01431160500522700.
Conners, R. W., Harlow, C. A. (1980). A Theoretical Comparison of Texture Algorithms. IEEE, Vol. PAMI-2, NO. 3, May 1980. pages 204 – 222. DOI: 10.1109/TPAMI.1980.4767008.
Curran, P. J. (1988). The Semivalqogram in Remote Sensing: An Introduction. Remote Sensing of Environment. Vol. 24, Issue 3, April 1988, Pages 493-507. https://doi.org/10.1016/0034-4257(88)90021-1.
Du Buf, J. M. H., Kardan, M., Spann, M. (1990). Texture feature performance for image segmentation. Pattern Recognition. Vol. 23, NO.3/4, Pages 291-309. https://doi.org/10.1016/0031-3203(90)90017-F.
Galloway, M. M. (1975). Texture Analysis Using Gray Level Run Lengths. Computer Graphics and Image Processing, 4, Pages 172-179. https://doi.org/10.1016/S0146-664X(75)80008-6.
Grebby, S., Cunningham, D., Naden, J., Tansey, K. (2010). Lithological mapping of the Troodos ophiolite, Cyprus, using airborne LiDAR. Remote Sensing of Environment 114, p. 713-724.
Grebby, S., Naden, J., Cunningham, D., Tansey, K. (2011). Integrating airborne multispectral imagery and airborne LiDAR data for enhanced lithological mapping in vegetated terrain. Remote Sensing of Environment.115(1):214-226. DOI:10.1016/j.rse.2010.08.019.
Hay, G. J., Niemann, K. O., McLean, G. F. (1996). An Object-Specific Image-Texture Analysis of H-Resolution Forest Imagery. Remote Sensing of Environment. Volume 55, Issue 2, Pages 108-122. https://doi.org/10.1016/0034-4257(95)00189-1.
Haralick, R. M., Shanmugam, K., Dinstein, I. (1973). Textural Features for Image Classification. IEEE, Vol. SMC-3, Issue: 6. Pages 610-621. DOI: 10.1109/TSMC.1973.4309314.
Julesz, B. (1975). Experiments in the Visual Perception of Texture. Scientific American , Vol. 232, No. 4, p. 34-43. DOI: 10.1038/scientificamerican0475-34.
Marceau, D. J., Howarth, P. J., Dubois, J. M., Gratton, D. J. (1990). Evaluation of the Grey-Level Co-Occurrence Matrix Method For Land-Cover Classification Using SPOT Imagery. IEEE, Vol. 28, No. 4, p. 513-519. DOI: 10.1109/TGRS.1990.572937.
Maxwell, A. E., Warner, T. A., Fang, F. (2018). Implementation of machine-learning classification in remote sensing: an applied review. International Journal of Remote Sensing. Vol. 39, Issue 9, p.2784-2871. DOI: 10.1080/01431161.2018.1433343.
Mills, H., Cutler, M. E. J., Fairbairn, D. (2007). Artificial neural networks for mapping regional‐scale upland vegetation from high spatial resolution imagery. International Journal of Remote Sensing, Vol. 27, No. 11, p.2177-2195, DOI: 10.1080/01431160500396501.
Ohanian, P. P., Dubes C. R. (1992). Performance evaluation for four classes of textural features. Volume 25, Issue 8, August 1992, Pages 819-833. https://doi.org/10.1016/0031-3203(92)90036-I.
Oon, A., Shafri, H. Z. M., Lechner, A. M., Azhar, B. (2019). Discriminating between large-scale oil palm plantations and smallholdings on tropical peatlands using vegetation indices and supervised classification of LANDSAT-8. International Journal of Remote Sensing, Vol. 40, No. 19, p. 7312-7328. DOI: 10.1080/01431161.2019.1579944.
Othman, A. A., Gloaguen, R. (2017). Integration of spectral, spatial and morphometric data into lithological mapping: A comparison of different Machine Learning Algorithms in the Kurdistan Region, NE Iraq. Journal of Asian Earth Sciences. Vol. 146, No. 15, p. 90-102. https://doi.org/10.1016/j.jseaes.2017.05.005.
Pacifici, F., Chini, M., Emery, W. J. (2009). A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification. Remote Sensing of Environment. Vol. 113, No. 6, p.1276-1292. DOI : 10.1016/j.rse.2009.02.014.
Paul, M. (1998). An evaluation of Landsat TM spectral data and SAR-derived textural information for lithological discrimination in the Red Sea Hills, Sudan, International Journal of Remote Sensing, vol. 19, no. 4, 587- 604.
Petrov, N. & Jordanov, I. N. (2011). Unsupervised Texture Image Classification using Self-Organizing Maps. https://www.researchgate.net/publication/268434714.
Rahman, M. M., Ullah, M. R., Lan, M., Sumantyo, J. T., Kuze, H. & Tateishi, R. (2012). Comparison of Landsat image classification methods for detecting mangrove forests in Sundarbans. International Journal of Remote Sensing.Vol. 34, No. 4, p.1041-1056. https://doi.org/10.1080/01431161.2012.717181.
Richards, J. A., Jia X. (2006). Remote Sensing Digital Image Analysis. An Introduction, 3rd revised and enlarged edition. ISBN 3 540 64860 7.
Shah, C. A., Varshney, P. K., Arora, M. K. (2007). ICA mixture model algorithm for unsupervised classification of remote sensing imagery. International Journal of Remote Sensing.Vol. 28, No. 8, p.1711-1731, DOI: 10.1080/01431160500462121.
Stanley, R. S., Hill, L. B., Chang, H. C., and Hu, H. N. (1981). A Transect Through The Metamorphic Core Of The Central Mountains, Southern Taiwan. Memoir of the Geological Society of China, 4, 443-473
Thakare, V. S. & Patil, N. N. (2014). Classification of Texture Using Gray Level Co-occurrence Matrix and Self-Organizing Map. International Conference on Electronic Systems, Signal Processing and Computing Technologies (ICESC). Pages 350–355. DOI 10.1109/ICESC.2014.66.
Trevisani, S., Cavalli, M., Marchi L. (2012). Surface texture analysis of a high-resolution DTM: Interpreting an alpine basin. Geomorphology. Vol. 161–162, p. 26-39. doi:10.1016/j.geomorph.2012.03.031.
Walton, G., Mills, G., Fotopoulos, G., Radovanovic R., Stancliffe, R. P. W. (2016) An approach for automated lithological classification of point clouds. Geosphere, Vol. 12 , No. 6, p.1833–1841. https://doi.org/10.1130/GES01326.1.
Weszka, J. S., Dyer, C. R., Rosenfeld, A. (1976). A Comparative Study of Texture Measures for Terrain Classification. IEEE, Vol. SMC-6, NO. 4, p. 269-285. DOI:10.1109/TSMC.1976.5408777.
Wulder, M. A., Coops, N. C., Roy, D. P., White, J. C. & Hermosilla, T. (2018). Land cover 2.0. International Journal of Remote Sensing. Vol. 39, Issue 12 , p. 4254-4284. https://doi.org/10.1080/01431161.2018.1452075.
Yıldırım, A. (2014). Unsupervised classification of multispectral Landsat images with multidimensional particle swarm optimization. International Journal of Remote Sensing, Vol. 35, NO. 4, p. 1217-1243, DOI: 10.1080/01431161.2013.877617.
Yen, T. P., Sheng, C. C., Keng, W. P., and Yang, Y. (1956). Some Problems On The Mesozoic Formation Of Taiwan. Bull. Geol. Suru. Taiwan, 8, 1-14.
Zhang, P., Qian, X., Guo, X., Yang, X., Li, G. (2020). Automated demarcation of the homogeneous domains of trace distribution within a rock mass based on GLCM and ISODATA. International Journal of Rock Mechanics and Mining Sciences. Vol. 128, 104249. https://doi.org/10.1016/j.ijrmms.2020.104249.