A comparison of selected classification algorithms for mappingbamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery

International Journal of Applied Earth Observation and Geoinformation

Volumn 26, Issue 1, 2014, Pages 298-311

  Ghosh, Aniruddha ^a   Joshi, P K ^a  

^a TERI UNIVERSITY   (India)

Author keywords

Bamboo mapping; Feature selection; GLCM texture; Pixel and object based classification; Random forest; Support vector machine; WorldView 2

Indexed keywords

ACCURACY ASSESSMENT; ALGORITHM; ARTIFICIAL INTELLIGENCE; BAMBOO; CLASSIFICATION; IMAGE ANALYSIS; LAND COVER; LAND USE; PIXEL; SATELLITE IMAGERY; TROPICAL ENVIRONMENT;

GANGETIC PLAIN; INDIA; WEST BENGAL;

EID: 84897586103     PISSN: 15698432     EISSN: 1872826X     Source Type: Journal    
DOI: 10.1016/j.jag.2013.08.011     Document Type: Article

References (64)

1. Arenas-Castro, S., Julien, Y., Jiménez-Muñoz, J.C., Sobrino, J.A., Fernández-Haeger,J., Jordano Barbudo, D., 2012. Mapping wild pear trees (Pyrus bourgaeana) inMediterranean forest using high-resolution QuickBird satellite imagery. Inter-national Journal of Remote Sensing 34 (9-10), 3376-3396.
2. Batista, M.H., Haertel, V., 2010. On the classification of remote sensing high spa-tial resolution image data. International Journal of Remote Sensing 31 (20),5533-5548.
3. Belluco, E., Camuffo, M., Ferrari, S., Modenese, L., Silvestri, S., Marani, A., Marani,M., 2006. Mapping salt-marsh vegetation by multispectral and hyperspectralremote sensing. Remote Sensing of Environment 105 (1), 54-67.
4. Blaschke, T., 2010. Object based image analysis for remote sensing. ISPRS Journal ofPhotogrammetry and Remote Sensing 65 (1), 2-16.
5. Breiman, L., 2001. Random forest. Machine Learning 45 (1), 5-32.
6. Breiman, L., Cutler, A., 2004. Random forests. http://stat-www.berkeley.edu/users/breiman/RandomForests/cc home.
7. Carleer, A., Wolff, E., 2004. Exploitation of very high resolution satellite data for treespecies identification. Photogrammetric Engineering and Remote Sensing 70 (1),135-140.
8. Cho, M.A., Mathieu, R., Asner, G.P., Naidoo, L., Van Aardt, J.A., Ramoelo, A.,Debba, P., Wessels, K., Main, R., Smit, I.P., Erasmus, B.F., 2012. Mappingtree species composition in South African savannas using an integrated air-borne spectral and LiDAR system. Remote Sensing of the Environment 125,214-226.
9. Clark, M.L., Roberts, D.A., Clark, D.B., 2005. Hyperspectral discrimination of tropicalrain forest tree species at leaf to crown scales. Remote Sensing of Environment96 (3-4), 375-398.
10. Chen, C.H., Ho, P.G.P., 2008. Statistical pattern recognition in remote sensing. PatternRecognition 41 (9), 2731-2741.
11. Chubey, M.S., Franklin, S.E., Wulder, M.A., 2006. Object-based analysis of Ikonos-2imagery for extraction of forest inventory parameters. Photogrammetric Engi-neering & Remote Sensing 72 (4), 383-394.
12. Cutler, D.R., Edwards, T.C., Beard, K.H., Cutler, A., Hess, K.T., Gibson, J.,Lawler, J.J., 2007. Random forests for classification in ecology. Ecology 88,2783-2792.
13. Dalponte, M., Bruzzone, L., Vescovo, L., Gianelle, D., 2009. The role of spectral reso-lution and classifier complexity in the analysis of hyperspectral images of forestareas. Remote Sensing of Environment 115 (11), 2345-2355.
14. Dalponte, M., Bruzzone, L., Gianelle, D., 2012. Tree species classification in theSouthern Alps based on the fusion of very high geometrical resolution multi-spectral/hyperspectral images and LiDAR data. Remote Sensing of Environment123, 258-270.
15. Dash, M., Liu, H., 1997. Feature selection for classification. Intelligent Data Analysis1, 131-156.
16. Duro, D.C., Franklin, S.E., Dubé, M.G., 2012. A comparison of pixel-based andobject-based image analysis with selected machine learning algorithms for theclassification of agricultural landscapes using SPOT-5 HRG imagery. RemoteSensing of Environment 118, 259-272.
17. Franklin, J.F., Maeda, T., Ohsumi, Y., Yagi, H., Hawk, M., 1979. Subalpine conif-erous forests of central Honshu, Japan. Ecological Monographs 49 (3),311-334.
18. Franklin, S.E., Hall, R.J., Moskal, L.M., Maudie, A.J., Lavigne, M.B., 2000. Incor-porating texture into classification of forest species composition fromairborne multispectral images. International Journal of Remote Sensing 21 (1),61-79.
19. Foody, G.M., 2004. Thematic map comparisons: evaluating the statistical signifi-cance of differences in classification accuracy. Photogrammetric Engineeringand Remote Sensing 70 (5), 627-633.
20. Ghosh, A., Joshi, P.K., 2013. Assessment of pan-sharpened very high res-olution WorldView 2 images. International Journal of Remote Sensing,http://dx.doi.org/10.1080/01431161.2013.838706.
21. Gitelson, A.A., Kaufman, Y.J., Merzlyak, M.N., 1996. Use of a green channel in remotesensing of global vegetation from EOS-MODIS. Remote Sensing of Environment58, 289-298.
22. Goswami, J., Tajo, L., Sarma, K.K., 2010. Bamboo resources mapping using satellitetechnology. Current Science 99 (5), 650-653.
23. Ham, J.S., Chen, Y., Crawford, M.M., Ghosh, J., 2005. Investigation of the randomforest framework for classification of hyperspectral data. IEEE Transactions onGeoscience and Remote Sensing 43 (3), 492-501.
24. Haralick, R.M., Shanmugam, K., Dinstein, I., 1973. Textural features for image classi-fication. IEEE Transactions on Systems, Man and Cybernetics 3 (6), 610-621.
25. Heinzel, J., Koch, B., 2012. Investigating multiple data sources for tree species clas-sification in temperate forest and use for single tree delineation. International Journal of Applied Earth Observation and Geoinformation 18, 101-110.
26. Hijmans, R.J., Etten, J.V., 2012. Raster: geographic data analysis and modeling. Rpackage version 2.0-41. http://CRAN.R-project.org/package=raster
27. Hughes, G.F., 1968. On the mean accuracy of statistical pattern recognizers. IEEETransactions on Information Theory 14, 55-63.
28. Immitzer, M., Atzberger, C., Koukal, T., 2012. Tree species classification with RandomForest using very high spatial resolution 8-Band WorldView-2 satellite data.Remote Sensing 4, 2661-2693.
29. Jensen, J.R., 2005. Introductory Digital Image Processing: A Remote Sensing Perspec-tive. Prentice Hall, Upper Saddle River.
30. Jones, H.G., Vaughan, R.A., 2010. Remote Sensing of Vegetation: Principles, Tech-niques, and Applications. Oxford University Press, Oxford.
31. Karatzoglou, A., Smola, A., Hornik, K., Zeileis, A., 2004. Kernlab: an S4 package forkernel methods in R. Journal of statistical software 11, 1-20.
32. Kuhn, M., 2012a. Variable selection using the caret package. http://cran.cermin.lipi.go.id/web/packages/caret/vignettes/caretSelection.pdf
33. Kuhn, M., 2012b. Contributions from Jed Wing, Steve Weston, Andre Williams, ChrisKeefer, Allan Engelhardt, Tony Cooper. In: Caret: classification and regressiontraining. R package version 5.15-052. http://CRAN.R-project.org/package=caret
34. Kuhn, M., 2008. Building predictive models in r using the caret package. Journal ofStatistical Software 28 (5), 1-26.
35. Leckie, D., Gillis, M., 1995. Forest inventory in Canada with an emphasis on mapproduction. Forestry Chronicle 71, 74-88.
36. Liaw, A., Wiener, M., 2002. Classification and regression by random forest. R News2, 18-22.
37. Linderman, M., Liu, J., Qi, J., An, L., Ouyang, Z., Yang, J., Tan, Y., 2004. Using artificialneural networks to map the spatial distribution of understory bamboo fromremote sensing data. International Journal of Remote Sensing 25 (9), 1685-1700.
38. Mairs, J.W., 1976. The use of remote sensing techniques to identify potential naturalareas in Oregon. Biological Conservation 9 (4), 259-266.
39. Mcnemar, Q., 1947. Note on the sampling error of the difference between correlatedproportions or percentages. Psychometrika 12, 153-157.
40. Mendez, G., Buskirk, T.D., Lohr, S., Haag, S., 2008. Factors associated with persistencein science and engineering majors: an exploratory study using classificationtrees and random forests. Journal of Engineering Education 97 (1), 57-70.
41. Menon, A.R.R., 1988. Utilization of remote sensing data in identifying bamboobrakes. In: Rao, I.V.R., et al. (Eds.), Bamboos: Current Research. Proceedings of theInternational Bamboo Workshop. Cochin, 14-18 November 1988. , pp. 47-50.
42. Menon, A.R.R., 1991. Remote sensing application in bamboo resources evaluation: acase study in Kerala. In: Proceedings of the 4th International Bamboo Workshop,Chiangmai, Thailand, 27-30 November 1991.
43. Melgani, F., Bruzzone, L., 2004. Classification of hyperspectral remote sensing imageswith support vector machines. IEEE Transactions on Geoscience and RemoteSensing 42 (8), 1778-1790.
44. Morain, S.A., 1986. Surveying China's agricultural resources: patterns and progressfrom space. Geocarto International 1 (1), 15-24.
45. Moskal, L.M., Franklin, S.E., 2002. Multistory forest stand discrimination with multi-scale texture from high spatial detail airborne imagery. Geocarto International17 (4), 53-66.
46. Mountrakis, G., Im, J., Ogole, C., 2011. Support vector machines in remote sensing: areview. ISPRS Journal of Photogrammetry and Remote Sensing 66 (3), 247-259.
47. Myint, S.W., Gober, P., Brazel, A., Grossman-Clarke, S., Weng, Q., 2011. Per-pixelvs. object-based classification of urban land cover extraction using high spatialresolution imagery. Remote Sensing of Environment 115, 1145-1161.
48. Nagendra, H., Rocchini, D., 2008. High resolution satellite imagery for tropicalbiodiversity studies: the devil is in the detail. Biodiversity Conservation 17,3431-3442.NBM, 2013. National Bamboo Mission. http://nbm.nic.in/
49. Pacifici, F., Chini, M., Emery, W.J., 2009. A neural network approach usingmulti-scale textural metrics from very high-resolution panchromatic imageryfor urban land-use classification. Remote Sensing of Environment 113 (6),1276-1292.
50. Pal, M., 2005. Random forest classifier for remote sensing classification. InternationalJournal of Remote Sensing 26 (1), 217-222.
51. Pal, M., Mather, M., 2005. Support vector machines for classificationin remote sensing. International Journal of Remote Sensing 26 (5),1007-1011.
52. Pathak, V., Dikshit, O., 2010. A new approach for finding an appropriate combi-nation of texture parameters for classification. Geocarto International 25 (4),295-313.
53. Peñuelas, J., Filella, I., Sweeano, L., 1993. The reflectance at the 970/900 region asan indicator of plant water status. International Journal of Remote Sensing 14, 1887-1905.
54. Pu, R., Landry, S., 2012. A comparative analysis of high spatial resolution IKONOSand WorldView-2 imagery for mapping urban tree species. Remote Sensing ofEnvironment 124, 516-533.
55. R Core Team, 2012. R: A Language and Environment for Statistical Computing. RFoundation for Statistical Computing, Vienna, Austria http://www.r-project.org/(ISBN 3-900051-07-0).
56. Richter, R., Schläpfer, D., 2011. Atmospheric/Topographic Correction for AirborneImagery. DLR report DLR-IB 565-02/11, Wessling, Germany.
57. Taylor, A.H., Qin, Z., 1997. The dynamics of temperate bamboo forests and pandaconservation in China. In: Chapman, G.P. (Ed.), The Bamboos. Academic Press,New York, pp. 189-203.
58. Trimble, 2010. eCognition® Developer 8.64.0 user guide, Available at:http://www.ecognition.com
59. Turner, W., Spector, S., Gardiner, N., Fladeland, M., Sterling, E., Steininger, M., 2003. Remote sensing for biodiversity science and conservation. Trends in Ecology andEvolution 18 (6), 306-314.
60. Vapnik, V.N., 2000. The Nature of Statistical Learning Theory. Springer, New York.
61. Wang, T., Skidmore, A.K., Toxopeus, A.G., Xuehua, L., 2009. Understory Bamboo Dis-crimination Using a Winter Image. Photogrammetric Engineering and RemoteSensing 75 (1), 37-47.
62. Wang, L., Sousa, W.P., Gong, P., Biging, G.S., 2004. Comparison of IKONOS and Quick-Bird images for mapping mangrove species on the Caribbean coast of Panama.Remote Sensing of Environment 91 (3-4), 432-440.
63. Waske, B., Benediktsson, J.A., Sveinsson, J.R., 2012. Random Forest classificationof Remote Sensing data. In: Chen, C.H. (Ed.), Signal and Image Processing forRemote Sensing. CRC Press, Boca Raton, FL, pp. 365-374.
64. Yu, Q., Gong, P., Clinton, N., Biging, G., Kelly, M., Schirokauer, D., 2006. Object-based detailed vegetation classification with airborne high spatial resolutionremote sensing imagery. Photogrammetric Engineering & Remote Sensing 72(7), 799-811.