成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	詹鈞評 Jhan, Jyun-Ping
論文名稱：	使用多尺度多階段物件導向影像分析技術進行崩塌地判釋 A Multi-scale/step Object Oriented Image Analysis Scheme for Landslide Recognition
指導教授：	饒見有 Rau, Jiann-Yeou
學位類別：	碩士 Master
系所名稱：	工學院 - 測量及空間資訊學系 Department of Geomatics
論文出版年：	2012
畢業學年度：	100
語文別：	英文
論文頁數：	77
中文關鍵詞：	物件導向影像分析、崩塌地偵測、陰影、數值地形模型
外文關鍵詞：	OBIA, Landslide detection, Shadow, DEM
相關次數：	點閱：129 下載：5
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

莫拉克颱風於2009年8月5日至10日間為南台灣帶來大量的豪雨，並在山區造成嚴重的崩塌與土石流，如廬山溫泉區、小林村、藤枝森林遊樂區等地區。本研究即採用不同平台如衛星、空載相機、無人飛行載具(UAV)，以獲取該地區之災後正射影像並結合空載光達產製之數值高程模型(DEM)與數值地表模型(DSM)進行崩塌地的影像判釋。然而傳統上進行影像判釋時，利用像元式的分類方式會造成椒鹽式雜訊使得成果並不合理，因此本研究即利用物件導向式影像分析方式(Object Oriented Analysis, OOA)提出一多尺度與多階段的崩塌地判釋方法。進行判釋時由於影像內容可能包含植被、建物、道路、雲、陰影、崩塌地等類別，因此本研究根據波譜資訊與物件分析推演出植生(NDVI/GRVI)、亮度(Brightness)、物高模型(OHM)、坡度(Slope)、密度(Density)及對比度(Contrast)等六種指標因子進行崩塌地與非崩塌地的分類。
在提出的多尺度崩塌地偵測方法中，其首先根據影像之空間解析度快速決定影像切割之初始尺度，並透過半自動的人工選取切割物件以決定各指標因子的門檻。而經切割後便利用該六種指標因子偵測崩塌地種子點作為第一階段之成果，接著利用較大的尺度進行區域成長法以合併和擴張崩塌地，經過再過濾後得到第二階段之成果。然而在區域成長法階段，因其無可避免的合併部分錯誤類別，因此便針對第二階段之成果以小尺度的再切割過濾錯誤後得到最終之精確崩塌地成果。同時由於藤枝地區受到嚴重的山丘陰影遮蔽的影響，僅使用波譜資訊無法有效偵測陰影覆蓋之崩塌地，因此另以此多尺度空間概念結合OHM指標與坡度資訊以萃取該地區之崩塌地。在成果方面發現經過三階段成果的精度評估後，本研究所提出之多尺度偵測流程可使整體精度提升至最高，同時結合陰影崩塌地之偵測方法亦可有效減少漏授比例並提升生產者精度及整體精度。

Taiwan was attacked by Typhoon Morakot during 5-10 Aug. 2009, which brings a huge amount of cumulative rainfall and caused lots of landslides in the mountainous area, such as in the Xiao Lin village, Lu San spring region, and Teng Zhi area. In this study for the purpose of performing multi-scale/step object-based landslide detection, we utilize images acquired from different platforms through Formosat-2 satellite, an airplane, and an unmanned-aerial vehicle (UAV) that equipped with DSLR digital camera as well as digital elevation model (DEM) and digital surface model (DSM) derived from airborne LiDAR system.
In traditional image analysis methods, pixel-based classification generally causes pepper and salt noise that will decrease the overall accuracy. Hence, in this study based on object-based image analysis (OBIA) we proposed a multi-scale/step landslide detection scheme. For landslide classification, considering image may contain vegetation, buildings, roads, cloud, shadow, and landslides, six feature indices are derived from spectral, topographical, and object shape information, such as vegetation index, brightness, slope, object height model (OHM), density, and contrast. In the multiresolution segmentation, image is segmented through a root-scale that is determined by the image spatial resolution and the thresholds for feature indices are determined manually by selecting some training samples. In the first, the preliminary landslide results are classified as landslide seeds and then we adopt region growing on seed objects with 1.5 times of the root-scale to expand the landslide regions. In the final, a down scale segmentation is applied on the expanded objects with a 0.75 times of the root-scale to remove some small patches errors. However, considering that landslides may be covered by shadow, we also develop a shadow landslide detection method based on the same multi-scale/step classification idea to reduce the omission errors.
After evaluation accuracy assessment through three stages of landslide detection, we conclude that the proposed scheme can optimize the results and get a maximum value of overall accuracy. Meanwhile, after shadow landslide detection the omission error is reduced. It is a major contribution of this study, particular for images acquired during the winter season or has low sun elevation angles.

摘要	I
Abstract	II
致謝	III
CONTENTS    IV
LIST OF TABLES	VIII
LIST OF FIGURES	X
CHAPTER 1 INTRODUCTION	1
1.1	Motivation	2
1.2	Image Classification Methods	2
1.2.1 Pixel-based Image Classification	2
1.2.2 Object-based Image Analysis	3
1.3	Introduction of Landslide	4
1.3.1 Mechanism of Landslide	4
1.3.2 Landslide Types	5
1.4	Material and Study Area	8
1.5	Paper Structure	10
CHAPTER 2 IMAGE SEGMENTATION	12
2.1	Image Segmentation	12
2.2	Multiresolution Segmentation	13
2.2.1 Shape & Compactness	13
2.2.2 Scale	14
2.2.3 Layer Weighting	15
CHAPTER 3 LANDSLIDE FEATURE AND CLASSIFICATION	16
3.1	Feature indices	16
3.1.1 Vegetation Index	17
3.1.2 Brightness	17
3.1.3 Slope	18
3.1.4 Object Height Model	19
3.1.5 Density	19
3.1.6 Contrast	21
3.1.7 Summary of Class Feature	22
3.2	Classification Methods	23
CHAPTER 4 Multi-scale/step Landslide Detection	25
4.1	Initial Segmentation	26
4.2	Collection of Landslide References	27
4.3	Training Stage	27
4.4	Multi-scale/step landslide detection	28
4.4.1 Seed-point Stage	28
4.4.2 Region Growing Stage	29
4.4.3 Precise Classification Stage	30
4.5	Shadow Landslide Detection	31
4.6	Accuracy Assessment	32
CHAPTER 5 CASE STUDIES AND ANALYSES	33
5.1	Shiaolin Village	33
5.2	Lu San	35
5.3	Teng Zhi	39
5.3.1 Pre-event image with pre-event DEM	39
5.3.2 Post-event image using pre-DEM	41
5.3.3 Post-event image with post-event DEM and DSM	42
5.3.4 Post-event image with SURF matched DEM	43
5.3.5 Shadow landslide detection	45
CHAPTER 6 DISCUSSIONS	47
6.1	Landslide Detection Results of each Stage	47
6.2	Determination of Scale Parameter	48
6.3	Training Sample	50
6.4	Detected Landslide Area	50
6.5	Fuzzy Threshold Determination	51
6.6	Producer Accuracy	52
6.7	SURF matched DSM	53
6.8	Inconsistence between Ortho-image and DEM	55
6.9	OHM Index	56
6.10	Vegetation Index	56
CHAPTER 7 CONCLUSIONS	58
REFERENCES	60
APPENDIX A AUTOMATIC TIE-POINT IMAGE MATCHING	64
A.1	Review of Image Matching	64
A.1.1 Area-based image matching	64
A.1.2 Feature-based Image Matching	64
A.2	Speed-up Robust Feature (SURF)	66
A.2.1 Integral Image	66
A.2.2 Feature Detector	66
A.2.3 Feature Descriptor	67
A.2.4 Matching	68
A.3	Proposed Scheme	68
A.3.1 Matching Strategy	69
A.3.2 Robust Error Filter	70
A.3.3 Labeling	71
A.3.4 Aerial Triangulation	71
A.3.5 Back-projection Point Transfer	71
A.4	Case Study	71
A.4.1 Close-range Images	72
A.4.2 UAV Images	74
APPENDIX B CONFUSION MATRIX	75
                                    

Aksoy, B., Ercanoglu, M., 2012. Landslide identification and classification by object-based image analysis and fuzzy logic: An example from the Azdavay region (Kastamonu, Turkey). Computers & Geosciences 38, 87-98.
Barazzetti, L., Scaioni, M., Remondino, F., 2010. Orientation and 3D modeling from markless terrestrial images: combining accuracy with automation. The Photogrammetric Record 25(132), 356-381.
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L., 2008. Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding 110, 346-359.
Benz, U.C., Hofmann, P., Willhauck, G., Lingenfelder, I., Heynen, M., 2004. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing 58, 239-258.
Blaschke, T., 2010. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 65, 2-16.
Cao, Y., McDonald, J., 2012. Improved feature extraction and matching in urban environments based on 3D viewpoint normalization. Computer Vision and Image Understanding 116, 86-101.
Cheng, C.-J., Rau, R.-J., Rau, J.-Y., 2010. Automatic Landslides Detection Using Object-Based Image Analysis with Aerial Ortho-imagery and Airborne LiDAR Data, Earth Sciences National Cheng Kung University, p. 150.
Cruden, D.M., Varnes, D.J., 1996. Landslide types and processes., in: Turner, A.K., Schuster, L.R. (Eds.), Transportation Research Board Special Report pp. 36-75.
Drǎguţ, L., Tiede, D., Levick, S.R., 2010. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. International Journal of Geographical Information Science 24, 859-871.
eCognition, 2011. eCognition Developer Reference Book. Trimble Germany GmbH, Trappentreustr., München, Germany.
ENVI, 2009. ENVI User's Guide ITT Visual Information Solutions
Fathi, H., Brilakis, I., 2011. Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features. Advanced Engineering Informatics 25, 760-770.
Gruen, A.W., 1985. Adaprive Least Squares Correlation. Photogrammetry, Remote Sensing and Cartography 14, 175-187.
Haralick, R.M., Shanmugam, K., Dinstein, I.H., 1973. Textural Features for Image Classification. TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS SMC-3, 610-621.
Harris, C., Stephens, M., 1988. A combined corner and edge detector, Fourth Alvey Vision Conference, Manchester,UK, pp. 147-151.
Hirschmuller, H., 2005. Accurate and efficient stereo processing by semi-global matching and mutual information, Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, pp. 807-814 vol. 802.
Hung, J.-J., 2000. Chi-Chi Earthquake Induced Landslides in Taiwan. Earthquake Engineering and Engineering Seismology 2, 25-33.
Johnson, B., Xie, Z., 2011. Unsupervised image segmentation evaluation and refinement using a multi-scale approach. ISPRS Journal of Photogrammetry and Remote Sensing 66, 473-483.
Juan, L., Gwun, O., 2010. SURF applied in Panorama Image Stitching, Image Processing Theory, Tools and Applications (IPTA), pp. 495-499.
Ke, Y., Sukthankar, R., 2004. PCA-SIFT: A More Distinctive Representation for Local Image Descriptors, Computer Vision and Pattern Recognition.
Lillesand, T.M., Kiefer, R.W., Chipman, J.W., 2004. Remote Sensing and Image Interpretation, 4th ed. John Wiley & Sons.
Lowe, D.G., 2004. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91-110.
Madej, M.A., 2011. Temporal and Spatial Distrubution of Landslides in the Redwood Creek Basin, Northern California, The Fourth Interagency Conference on Research in the Watersheds, Fairbanks, AK.
Malamud, B.D., Turcotte, D.L., Guzzetti, F., Reichenbach, P., 2004. Landslide inventories and their statistical properties. Earth Surface Processes and Landforms 29, 687-711.
Martha, T.R., Kerle, N., Jetten, V., van Westen, C.J., Kumar, K.V., 2010. Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods. Geomorphology 116, 24-36.
Martha, T.R., Kerle, N., van Westen, C.J., Jetten, V., Vinod Kumar, K., 2012. Object-oriented analysis of multi-temporal panchromatic images for creation of historical landslide inventories. ISPRS Journal of Photogrammetry and Remote Sensing 67, 105-119.
Mikolajczyk, K., Schmid, C., 2005. A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 1615-1630.
NCDR, 2010. Disaster Survey and Analysis of Morakot Typhoon. National Science and Technology Center for Disaster Reduction (NCDR), p. 119.
Niethammer, U., James, M.R., Rothmund, S., Travelletti, J., Joswig, M., 2012. UAV-based remote sensing of the Super-Sauze landslide: Evaluation and results. Engineering Geology 128, 2-11.
Popescu, M.E., 2002. Landslide Causal Factors and Landslide Remediatial Options, International Conference on Landslides, Singapore.
Rau, J.-Y., Chang, K.-T., Shao, Y.-C., Lau, C.-C., 2011. Semi-automatic shallow landslide detection by the integration of airborne imagery and laser scanning data. Natural Hazards 61, 469-480.
Rau, J.-Y., Chen, L.-C., Liu, J.-K., Wu, T.-H., 2007. Dynamics monitoring and disaster assessment for watershed management using time-series satellite images. IEEE Transactions on Geoscience and Remote Sensing 45, 1641-1649.
Rosten, E., Porter, R., Drummond, T., 2010. Faster and Better: A Machine Learning Approach to Corner Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 32.
Stumpf, A., Kerle, N., 2011. Object-oriented mapping of landslides using Random Forests. Remote Sensing of Environment 115, 2564-2577.
Tsai, F., Hwang, J.H., Chen, L.C., Lin, T.H., 2010. Post-disaster assessment of landslides in southern Taiwan after 2009 Typhoon Morakot using remote sensing and spatial analysis. Natural Hazards and Earth System Science 10, 2179-2190.
Tucker, C.J., 1979. Red and Photographic Infrared linear Combinations for Monitoring Vegetation. Remote Sensing of Enviroment 8, 127-150.
USGS, 2004. Landslide Types and Processes. U.S. Department of Interior, U.S. Geological Survey.
Valgren, C., Lilienthal, A.J., 2010. SIFT, SURF & seasons: Appearance-based long-term localization in outdoor environments. Robotics and Autonomous Systems 58, 149-156.
Varnes, D.J., 1978. Slope movement types and processes, in: Schuster, R.L., and Krizek, R.J (Ed.), Landslides Analysis and Control. National Research Council, Washington, D.C., Transportation Research Board, pp. 11-33.
Vu, T.T., Yamazaki, F., Matsuoka, M., 2009. Multi-scale solution for building extraction from LiDAR and image data. International Journal of Applied Earth Observation and Geoinformation 11, 281-289.
Werner, H., 1984. Automatic Gross Error Detection by Robust Estimators, International Archives of Photogrammetry and Remote Sensing, pp. 1101-1108.
Yu, S.-B., Chen, H.-Y., Kuo, L.-C., 1997. Velocity field of GPS stations in the Taiwan area. Tectonophysics 274, 41-59.

校內：立即公開
校外：立即公開

簡易檢索 / 詳目顯示

相關論文