近年來，相關研究使用機器學習方法中的監督式分類，搭配空載光達與數位影像資料，對都會區之建物、樹木、道路及草地等地物類別進行影像分類。本研究先使用全彩航照影像、光達之高度及反射強度資料，再結合光達的正規化高度(nDSM)進行都會地區之地物分類，隨後再使用高度分層的概念分類。依據三層式高度混合式分類分類架構(黃明哲，2007)，提出兩層式高度混合式分類分類。在分類過程中，依據各地物類別在特徵空間(feature space)不同的分布叢集，發現同屬性而不同高度之道路與房屋，及草地與樹木，重疊情形最為明顯，極易造成傳統分類演算法分類混淆的情形。所以可藉由加入高度資訊解決同屬性不同高度之地物在特徵空間重疊性之問題，進而提高分類精度。經比較不同高度分層方式的分類結果，兩層式高度混合式分類分層較三層式高度混合式分類者之混合式分類結果為佳。
本文以三層式的高度分層規則分類(rule-based classification)架構為基礎，提出兩層式的規則分類架構，從新的觀點詮釋高度資訊在地物分類上所扮演角色的重要性，藉由簡化高度規則的制定及樣本訓練過程提高都市地物的分類精度。若傳統分類方法加入正規化高度資訊，所得到之分類精度結果比未加入正規化高度分類更佳。另外為探討加入高度分層的分類規則是否適用其他分類方法，本研究加入高度分層分類規則到演算法較複雜的類神經網路分類法與支持向量機分類法，由其分類精度結果顯示均較原分類方法結果為佳。然而，以時間成本探討，類神經網路分類(BPN)與支持向量機分類(SVM)法，在參數尋找以及運算量，比高斯最大似然分類法(MLC)所花費的資料處理時間高出許多，但分類的精度卻相當。因此使用演算法較不費時的MLC加上兩層式高度混合式分類法，所得到之分類精度或時效性，均比BPN與SVM為佳。

In recent years, many researches focused on the supervised machine learning classification methods using Lidar and remotely sensed image to provide buildings, trees, roads, and grass categories for urban ground feature classification. First, this research performed urban ground feature classification based on true color aerial imagey and Lidar Intensity. Second, Lidar derived normalized DSM (nDSM) was added to the classification. Finally, the concept of height level rules was applied. This research utilized two-level height rule-based classification exteneded from three-level height rule-based classification (Huang, 2007). It is obvious to observ the overlap for the roads and houses, and grass and trees in the feature space plot where result in the classification confusion. These confusions can be resolved by fusion the height information. After comparing classification accuracy, the two-level height is better than three-level height classification scheme.
This research proposed hybrid classification method based on Maximum likelihood classification (MLC) and two-level height rules. This method reveals the role of height information in urban ground feature classification. The height level rules were also applied to other supervised classification method such as Back-Propagation Network (BPN) and Support Vector Machine (SVM). The classification results show that the accuracy of hybrid method is better than the orgional classification method. However, the time required to look for the classification parameters for BPN and SVM is greater than MLC but only can derived considerable results. Therefore, the hybrid classification method based on MLC is better than other two methods.

目錄
中文摘要 I
Abstract II
致謝 III
目錄 IV
圖目錄 VII
表目錄 X
第一章 前言 1
1-1 研究動機 1
1-2 文獻回顧 1
1-3 研究目的與構想 4
第二章 影像分類方法 7
2-1 高斯最大似然分類法 7
2-2 倒傳式類神經網路分類法 8
2-2-1 倒傳式網路原理與架構 8
2-2-2 倒傳式網路學習法則與學習過程 10
2-3 支持向量機分類法 13
2-3-1 線性可分 14
2-3-2 線性不可分 15
第三章 融合光達高度之混合式分類法 18
3-1 波譜空間 18
3-2 特徵空間分析 21
3-2-1 地物特徵混淆分析 21
3-2-2 實驗區樣本之分離度分析 22
3-2-3 都市區地物高度直方圖分析 23
3-3 知識庫規則分類高度分層規則 25
3-3-1 三層式高度混合式分類分類規則 25
3-3-2 兩層式高度混合式分類分類規則 26
3-4 高度分層規則與傳統監督式分類方法結合 26
第四章 實驗結果與討論 30
4-1 實驗區資訊 30
4-2 特徵向量 32
4-2-1 RGB影像 32
4-2-2 光達反射強度( Lidar Intensity)影像 33
4-2-3 正規化高度(nDSM)影像 33
4-3 選取實驗區之訓練樣本與測試樣本 35
4-4 分類精度評估 38
4-5 監督式影像分類 41
4-5-1 全彩影像與光達反射強度分類結果(實驗區A) 42
4-5-2 加入正規化高度分類結果(實驗區A) 45
4-5-3 全彩影像與光達反射強度分類結果(實驗區B) 47
4-5-4 加入正規化高度分類結果(實驗區B) 50
4-5-5 光譜影像與是否加入正規化高度分類結果討論 52
4-6 混合式影像分類 54
4-6-1 三層式高度混合式分類法分類結果(實驗區A) 57
4-6-2 三層式高度混合式分類法分類結果(實驗區B) 60
4-6-3 兩層式高度混合式分類法分類結果(實驗區A) 63
4-6-4 兩層式高度混合式分類法分類結果(實驗區B) 66
4-6-5 混合式分類法之結果討論 69
4-7 混合式分類與傳統影像分類結果比較與討論 71
第五章 結論與建議 78
5-1 結論 78
5-2 建議 80
參考文獻 82
附錄 85

林承毅，2004. 空載雷射掃描資料產生數值高程模型之研究，國立高雄應用科技大學土木工程與防災科技研究所碩士論文.
黃明哲，2007. 應用航測影像及光達資料探討以知識庫為基礎之都市地物特徵分類之研究，國立中山大學海洋環境及工程研究所博士論文.
梅建新，2004. 基於支持向量機的高分辨率遙感影像的目標檢測研究，武漢大學博士論文
Arefi, H., M. Hahn, J. Lindenberger, 2003. LIDAR data classification with remote Sensing tools. Proceedings of the ISPRS Commission IV Joint Workshop Challenges in Geospatial Analysis, Integration and Visualization II, September 8 - 9, 2003, Stuttgart, Germany. Page 131-136
Baltsavias, P. E. and A. Gruen, 2003. A comparison of aerial photos, LIDAR and IKONOS for monitoring cities. Remotely Sensed Cities (Mesev, V.). Taylor & Francis, New York, 368p
Blaschke, T., M. Conradi and S. Lang, 2001. Multi-scale image analysis for ecological monitoring of heterogeneous, small structured landscapes, Proceedings of SPIE, Toulouse, pp. 35-44
Carleer, P. A., O. Debeir, and E. Wolff, 2005. Assessment of Very High Spatial Resolution Satellite Image Segmentations. Photogrammetric Engineering & Remote Sensing, 71(11): 1285–1294.
Charaniya, A., R. Manduchi, S. Lodha, 2004. Supervised Paramteric Classification of LiDAR Data. IEEE Workshop on Real Time 3D Sensor and Their Use, Washington DC, June 2004
Cohen, Y. and M. Shoshany, 2002. A national knowledge-based crop recognition in Mediterranean environment. International Journal of Applied Earth Observation and Geoinformation Vol. 4 (2002) 75–87
Congalton, R. ,1991. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, pp. 35-46.
Davis, S.M., Landgrebe, D.A., Phillips, T.L., Swain, P.H., Hoffer, R.M., Lindenlaub, J.C., and Silva, L.F. ,1978. Remote sensing: The quantitative approach.
Guindon, B., Y. Zhang, C. Dillabaugh, 2004. Landsat urban mapping based on a combined spectral–spatial methodology. Remote Sensing of Environment Vol. 92 (2004) 218–232
Haala, N. and C. Brenner, 1999. Extraction of buildings and trees in urban environment. ISPRS Journal of Photogrammetry and Remote Sensing, 54(2-3): 130-137.
Hill, A. R., G. M. Smith, R. M. Fuller, and N. Veitch, 2002. Landscape modelling using integrated airborne multi-spectral and laser scanning data. International Journal of Remote Sensing, vol. 23, no. 11, 2327–2334.
Hodgson, E. M., J. R. Jensen, J. A. Tullis, K. D. Riordan, and C. M. Archer, 2003. Synergistic Use of Lidar and Color Aerial Photography for Mapping Urban Parcel Imperviousness. Photogrammetric Engineering & Remote Sensing Vol. 69, No. 9, pp. 973–980.
Jensen, J.R. (2005). Remote Sensing of Environment: An Earth Resource Perspective, Prentice-Hall, Inc., 2nd Edition.
Lee, L. W., M.J. Huang, S. W. Shyue, 2008. An Adaptive Filtering and Terrain Recovery Approach for Airborne LiDAR Data. International Journal of Innovative Computing, Information and Control, 1783-1796
Liu, X. H., A.K. Skidmore, H. V. Oosten, 2002. Integration of classification methods for improvement of land-cover map accuracy. ISPRS Journal of Photogrammetry & Remote Sensing 56 (2002) 257– 268.
Rego, F. and B. Koch, 2003. Automatic classification of land cover with high resolution data of the Rio de Janeiro city Brazil comparison between pixel and object classification. Proceedings of The International archives of the photogrammetry, remote sensing and spatial information sciences, Carstens, J. ed., Regensburg, Germany, 27-29 June.
Repaka, R. S., E. Kolstad, C. G. O’Hara, 2004. Comparing Spectral and Object Based Approaches for Classification and Transportation Feature Extraction from High Resolution Multispectral Imagery. ASPRS Annual Conference Proceedings May 2004, Denver, Colorado.
Richards, J. A. and X. Jia, 1999, Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin, 363p.
Rottensteiner, F., J. Trinder, S. Clode, and K. Kubik, 2005. Using the Dempster-Shafer method for the fusion of lidar data and multispectral images for building detection, Information Fusion, 6(4): 282-300
Stefanov, W. L., M. S. Ramsey, P. R. Christensen, 2001. Monitoring urban land cover change: An expert system approach to land cover classification of semiarid to arid urban centers. Remote Sensing of Environment Vol. 77 (2001) 173– 185
Sun, W., V. Heidt, P. Gong, and G. Xu, 2003. Information Fusion for Rural Land-Use Classification With High-Resolution Satellite Imagery. IEEE Transactions on Geoscience and Remote Sensing, Vol. 41, No. 4, April 2003.
Syed, S., P. Dare and S. Jones, 2005. Automatic classification of land cover features with high resolution imagery and lidar data: an object-oriented approach. Proceedings of SSC2005 Spatial Intelligence, Innovation and Praxis: The national biennial Conference of the Spatial Sciences Institute, September, 2005.
Tao, G. and Y. Yasuoka, 2002. Combining High Resolution Satellite Imagery and Airborne Laser Scanning Data for Generating bareland DEM in Urban Areas, Proceedings of International Workshop on Visualization and Animation of Landscape, International Archives of Photogrammetry, Remote Sensing and Spatial Information Science, Kunming, China, 26 - 28 February 2002.
Taubenböck, H., T. Esch, and A. Roth, 2006. An Urban Classification Approach Based on an Object–Oriented Analysis of High Resolution Satellite Imagery for a Spatial Structuring Within Urban Areas. 1st EARSeL Workshop of the SIG Urban Remote Sensing Humboldt-Universität zu Berlin, 2-3 March 2006.
Thomas, N., C. Hendrix, and R. G. Congalton, 2003. A Comparison of Urban Mapping Methods Using High-Resolution Digital Imagery. Photogrammetric Engineering & Remote Sensing Vol. 69, No. 9, pp. 963–972.
Vapnik V N. 1998, Statistical Learning Theory. Wiley, New York
Wentz, A. E., W. L. Stefanov, C. Gries, and D. Hope, 2006. Land use and land cover mapping from diverse data sources for an arid urban environments. Computers, Environment and Urban Systems Vol. 30 (2006) 320–346.
Weidner, U., and W. Förstner, 1995. Towards automatic building extraction from high-resolution digital elevation models, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 50, pp.38–49.