An Object-oriented Analysis for Characterizing the Rainfall-induced Shallow Landslide

10.6119/JMST-012-0430-2

Kuan-Tsung Chang；Jin-King Liu；Chu-I Wang

landslides ； SPOT ； LiDAR ； segmentation ； SVM

Journal of Marine Science and Technology

20卷6期（2012 / 12 / 01）

647 - 656

英文

Landslides are natural phenomena for the dynamic balance of the earth's surface. Because of frequent occurrences of typhoons and earthquakes in Taiwan, mass movements are common threats to people's lives. In this paper, the interpretation of knowledge is quantified as recognition criteria. Multisource high-resolution data, for example, a SPOT satellite image, 20m×20m Digital Terrain Model (DTM) reduced from Light Detection And Ranging (LiDAR) data, and aerial orthophotos were used to construct the feature space for landslide analysis. Landslides were recognized by an object-oriented method combining edge-based segmentation and a Supported Vector Machine (SVM) method. The classification results are evaluated in comparison with those by manual interpretation. Two cases from northern and central Taiwan are tested. Both cases show that the object-based SVM method is better than a pixel-based method in classification accuracy. The commission error of the proposed method is also smaller than that of the pixel-based method. Moreover, except for the spectral features, the slope and Object Height Model (OHM) characteristics are also important factors for improving landslide classification accuracy. Further study is required for assessing the mixed pixel effect when the resolution is as large as 20 m and for characterizing the effects of sampling rates or scaling caused by changes in resolution.

1. Barlow, J., Martin Y., and Franklin, S. E., “Detecting translational landslide scars using segmentation of Landsat ETM+ and DEM data in the northern Cascade Mountains, British Columbia,” Canadian Journal of Remote Sensing, Vol. 29, No. 4, pp. 510-517 (2003).
   連結：
2. Burges, J., “A tutorial on support vector machines for pattern recongnition,” Data Mining and Knowledge Discovery, Vol. 2, pp. 121-167 (1998).
   連結：
3. Carleer, A., Debeir, O., and Wolff, E., “Comparison of very high spatial resolution satellite image segmenations,” Proceedings of SPIE Image and Signal Processing for Remote Sensing IX, Vol. 5238, pp. 532-542 (2004).
   連結：
4. Chang, K. T., Hwang, J. T., Liu, J. K., Wang, E. H., and Wang, C. I., “Apply two hybrid methods on the Rainfall-induced landslides interpretation,” Geoinformatic 2011, Shanghai, China (2011).
   連結：
5. Chang, K. T., Wang, Z. Y., Kao, Q. X., and Liu, J. K., “A comparison of two OOA segmentation methods for the detection of rainfall-induced landslides using airborne LiDAR nDSM data,” The 2010 International congress on Computer applications and Computational Science (CACS2010), IRAST Press, Singapore (2010).
   連結：
6. Chapelle, O., Haffner, P., and Vapnik, V., “Support vector machines for histogram-based image lassification,” IEEE Transactions on Neural Networks, Vol. 10, No. 5, pp. 1055-1064 (1999).
   連結：
7. Guzzetti, F., Cardinali, M., Reichenbach, P., and Carrara, A., “Comparing landslide maps: a case study in the upper Tiber River Basin, central Italy,” Environmental Management , Vol. 25, No. 3, pp. 247-363 (2000).
   連結：
8. Huang, W. K., Lin, M. L., Chen, L. C., Lin, Y. H., and Hsiao, C. Y., “Applying object-oriented analysis to segmentation and classification of landslide and artificial facilities with remote sensing images,” Journal of photogrammetry and remote sensing,” Vol. 15, No. 1, pp. 29-49 (2010). (in Chinese)
   連結：
9. Hwang, J. and Chiang, H., “The study of high resolution satellite image classification based on Support Vector Machine,” Geoinformatic 2010, Beijing, China (2010).
   連結：
10. Liu, J. K., Chang, K. T., Rau, J. Y., Hsu, W. C., Liao, Z. Y., Lau, C. C., and Shih, T. Y., The Geomorphometry of Rainfall-Induced Landslides in Taiwan Obtained by Airborne Lidar and Digital Photography, Geoscience and Remote Sensing, In-Tech, Inc. (2009).
    連結：
11. Mantovani, F., Soeters, R., and Van, C. J., “Remote sensing techniques for landslide studies and hazard zonation in Europe,” Geomorphology, Vol. 15, pp. 213-225 (1996).
    連結：
12. McKean, J. E., Acker, S. A., Fitt, B. J., Renslow, M., Emerson, L., and Hendrix, C. J., “Objective landslide detectoin and surface morphology mapping using high-resolution airborne laser altimetry,” Geomorphology, Vol. 57, pp. 331-351 (2004).
    連結：
13. McKean, N. F., Streutker, D. R., Chadwick, K., Glenn, D. J., Thackray, G. D., and Dorsch, S. J., “Analysis of LiDar-derived topographic information for characterizing and differentiating landslide morphology and activity,” Geomorphology, Vol. 73, pp. 131-148, DOI: 10.1016/j.geomorph.2005.07.006 (2005).
    連結：
14. Nichol, J. and Wong, M. S., “Satellite remote sensing for detailed land slide inventories using change detection and image fusion,” International Journal of Remote Sensing, Vol. 26, No. 9, pp. 1913-1926 (2005).
    連結：
15. Parise, M., “Landslide mapping techniques and their use in the assessment of the landslide hazard,” Physics and Chemistry of the Earth, Vol. 26, No. 9, pp. 697-703, DOI: 10.1016/S1464-1917(01)00069-1 (2001).
    連結：
16. Schulz, W. H., “Landslide susceptibility revealed by LiDAR imagery and historical records,” Seattle, Washington, Engineering Geology, Vol. 89, Nos. 1-2, pp. 67-87, DOI: 10.1016/j.enggeo.2006.09.019 (2007)
    連結：
17. Van, S. and Seijmonsbergen, A. C., “Expert-driven semi-automated geomorphological mapping for a mountainous area using a laser DTM,” Geomorphology Vol. 78, pp. 309-320 (2006).
    連結：
18. Zanutta, A., Baldi, P., Bitelli, G., Cardinali, M., and Carrara, A., “Qualitative and quantitative photogrammetric techniques for multi-temporal landslide analysis,” Annals of Geophysics, Vol. 49, Nos. 4/5, pp. 1067- 1080 (2006).
    連結：
19. Canty, M. J., Image Analysis, Classification, and Change Detection in Remote Sensing : With Algorithms for ENVI/IDL, CRC Press, Taylor & Francis Group (2010).
20. Chang, K. T., Kao, Q. X., Wang, Z. Y., and Liu, J. K., “Automatic rainfall- induced landslide interpretation and features analysis, special issue for disaster prevention,” Journal of Photogrammetry and Remote Sensing, Vol. 15, No. 1, pp. 79-95 (2010). (in Chinese)
21. Chang, K. T. and Liu, J. K., “Landslide features interpreted by neural network method,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Istanbul, Turkey, Vol. XX, Part B7, pp. 574-579 (2004).
22. Chang, K. T., Liu, J. K., Chang, Y. M., and Kao, C. S., “An accuracy comparison for the landslide inventory with the BPNN and SVM methods,” Gi4DM 2010, Turino, Italy (2010).
23. Chen, C. C., Rice Paddy Identification using the Support Vector Machine and Plausible Neural Network, MSc Thesis, Department of Civil Engineering, NCTU, HsinChu, Taiwan (2006). (in Chinese)
24. Delacourt, C., Allemand, P., Squarzoni, C., Picard, F., Raucoules, D., and Carnec, C., “Potential and limitation of ERS-Differential SAR interferometry for landslide studies in the French Alps and Pyrenees,” Proceedings of FRINGE 2003 Workshop, Frascati, Italy (2003).
25. Dilley, M., Chen, R. S., Deichmann, U., Lerner-Lam, A. L., Arnold, M., Agwe, J., Buys, P., Kjekstad, O., Lyon, B., and Yteman, G., Natural Disaster Hotspots: A Global Risk Analysis, Disaster Risk Management Series No.5, The World Bank, Washington, D.C. (2005).
26. Eeckhaut, V. D., Poesen, M. J., Verstraeten, G., Vanacker, V., Nyssen, J. Moeyersons, Van, J., and Vandekerckhove, L. P. H., “Use of LiDARderived images for mapping old landslides under forest,” Earth Surface Processes and Landforms, Vol. 32, No. 5, pp. 754-769 (2007).
27. Galli, M., Ardizzone, F., Cardinali, M., Guzzetti, F., and Reichenbach, P.,“Comparing landslide inventory maps,” Geomorphology, Vol. 94, pp. 268-289 (2008).
28. Hong, K. C., Landslide Detection Using Various Features from Multispectral Imagery, Master Thesis, Department of Geomatics, National Cheng Kung University, Tainan, Taiwan (2009). (in Chinese)
29. ITT, ENVI EX User’s Guide (2010).
30. Jain, A. K. and Dubes, R. C., Algorithms for Clustering Data, Prentice Hall, Inc (1988)
31. Jhan, J. P. and Rau J. Y. “A four-stage object-based segmentation and classification scheme for landslide detection,” Proceedings of Asian Conference on Remote Sensing 2011, Taipei, Taiwan (2011).
32. Jin, X., “Segmentation-based image processing system,” US Patent 20090123070, filed Nov. 14, 2007, and issued May 14 (2009).
33. Kao, Q., Automatic Interpretation and Feature Analysis for the Rain-Fall Induced Landslide, Master Thesis, Minghsin University of Science and Technology, HsinChu, Taiwan (2010). (in Chinese)
34. Kerle, N. and Martha, T. R., “The potential of object-based and cognitive methods for rapid detection and charcterisation of landslides,” Gi4DM 2010, Turino, Italy (2010).
35. Kojima, H., Chung, C. F., and Westen, C. V., “Strategy on the landslide type analysis based on the expert knowledge and the quantitive prediction model,” International Archives of Photogrammetry and Remote Sensing, Vol. XXXIII, Part B7, pp. 701-708 (2000).
36. Lillesand, T. M., Kiefer, R. W., and Chipman, J. W., Romote Sensing and Image Interpretation, Fifth Edition, John Wiley & Sons, Inc. (2004).
37. Liu, J. K., Wong, S. J., Huang, J. H., and Huang, M. J., “Images analysis for landslides induced by torrential rainfall,” Proceedings of Symposium on Civil Engineering Technology and Management for 21 Century, Hsinchu, P.C-21~C-31 (2001).
38. Moine, M., Puissant, A., and Malet, J. P., “Detection of landslides from aerial and satellite images with a semi-automatic method. Application to the Barcelonnette basin (Alpes-de-Haute-Provence, France),” Landslide Process: from Geomorphological Mapping to Dynamic Modelling, pp. 63-68 (2009).
39. NFA, “Historical records of natural disasters of Taiwan from 1958 to 2007,” National Fire Agency, Ministry of the Interior, Access date: 31 December 2008, http://www.nfa.gov.tw/Show.aspx?MID=97&UID=827 &PID=97
40. Yang, M. S., Integrating LiDAR Derived Data and SPOT Multispectral Imagery for Landslides Classification, MSc Thesis, Department of Geography, NKNU, Kaohsiung, Taiwan (2007). (in Chinese)