Object-oriented mapping of urban trees using random forestclassifiers

International Journal of Applied Earth Observation and Geoinformation

Volumn 26, Issue 1, 2014, Pages 235-245

  Puissant, Anne ^a   Rougiera, Simon ^a   Stumpf, André ^a  

^a UNIVERSITÉ DE STRASBOURG   (France)

Author keywords

Feature selection; Object based image analysis; Random forest classifier; Urban trees; VHR satellite images

Indexed keywords

IMAGE ANALYSIS; IMAGE CLASSIFICATION; SATELLITE DATA; SATELLITE IMAGERY; SPATIAL RESOLUTION; TREE; URBAN AREA; URBAN DEVELOPMENT; URBAN FORESTRY; URBAN PLANNING; VEGETATION MAPPING;

ALSACE; BAS RHIN; FRANCE; STRASBOURG;

EID: 84897879307     PISSN: 15698432     EISSN: 1872826X     Source Type: Journal    
DOI: 10.1016/j.jag.2013.07.002     Document Type: Article

References (68)

1. Amro, I., Mateos, J., Vega, M., Molina, R., Katsaggelos, A., 2011. A survey of classicalmethods and new trends in pansharpening of multispectral images. EURASIPJournal on Advances in Signal Processing 79, 1-22
2. Ardila, J.P., Tolpekin, V.A., Bijker, W., Stein, A., 2011. Markov-random-field-basedsuper-resolution mapping for identification of urban trees in VHR images. ISPRSJournal of Photogrammetry and Remote Sensing 66, 762-775
3. Ardila, J.P., Bijker, W., Tolpekin, V.A., Stein, A., 2012. Context-sensitive extractionof tree crown objects in urban areas using VHR satellite images. InternationalJournal of Applied Earth Observation and Geoinformation 15, 57-69
4. Benz, U.C., Hofmann, P., Willhauck, G., Lingenfelder, I., Heynen, M., 2004. Multires-olution object-oriented fuzzy analysis of remote sensing data for GIS-readyinformation. ISPRS Journal of Photogrammetry and Remote Sensing 58,239-258
5. Blaschke, T., Strobl, J., 2001. What's wrong with pixels? Some recent developmentsinterfacing remote sensing. GIS - Journal of Geographic information Systems 6,12-17
6. Blaschke, T., 2010. Object-based image analysis for remote sensing. ISPRS Journal ofPhotogrammetry and Remote Sensing 65, 2-16
7. Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J., 1984. Classification and Regres-sion Trees. Chapman & Hall, New York
8. Breiman, L., 2001. Random forests. Machine Learning 45, 5-32
9. Breiman, L., 2003. RF tool - a class of two eyed algorithm. In: SIAM Workshop
10. Bottou, L., Lin, C.J., 2007. Support Vector Machine Support. Large Scale KernelMachine., pp. 301-320
11. Chan, J.C.W., Spanhove, T., Ma, J., Vanden Borre, J., Paelinckx, D., Canters, F.,2010. Natura 2000 identification and conservation status assessment withsuperresolution enhanced hyperspectral (CHRIS/Proba) imagery. Proceedingsof Geographic Object-Based Image Analysis 3 (Part 4/C7), Ghent, Belgium.
12. Comop, 2009. Trame Verte et Bleue: Orientations nationales pour la préservation etla restauration des continuités écologiques. Guide 2 - Appui méthodologique àl'élaboration regional de la TVB, Rapport du comité opérationnel TVB du Grenellede l'Environnement, Paris, 82p.
13. Congalton, R., 1991. A review of assessing the accuracy of classifications of remotelysensed data. Remote Sensing of Environment 37, 35-46.
14. Defienens, 2011. eCognition 8.64.1 Reference Book. Trimble Documentation,Munich, Germany
15. Dey, V., Zhang, Y., Zhong, M., 2010. A review on image segmentation techniqueswith remote sensing perspective. In: Proceedings of the International Societyfor Photogrammetry and Remote Sensing Symposium (ISPRS10), vol. XXXVIII(Part 7A), Austria, pp. 31-42.
16. Diaz-Uriarte, R., Alvarez de Andres, S., 2006. Gene selection and classification ofmicroarray data using random forest. BMC Bioinformatics, 7.
17. Dorigo, T., Lucieer, A., Podobnikar, T.,Čarni, A., 2012. Mapping invasive Fal-lopia japonica by combined spectral, spatial, and temporal analysis of digitalorthophotos. International Journal of Applied Earth Observation and Geoinfor-mation 19, 185-195
18. Drǎguţ, L., Tiede, D., Levick, S.R., 2010. ESP: a tool to estimate scale parameter for mul-tiresolution image segmentation of remotely sensed data. International Journalof Geographical Information Science 24, 859-871.
19. Duro, D.C., Franklin, S.E., Dubé, M.G., 2012a. 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.
20. Duro, D.C., Franklin, S.E., Dubé, M.C., 2012b. Multi-scale object-based image analysisand feature selection of multi-sensor earth observation imagery using randomforests. International Journal of Remote Sensing 33, 4226-4502.
21. Espindola, G.M., Camara, G., Reis, I.A., Bins, L.S., Monteiro, A.M., 2006. Parameterselection for region-growing image segmentation algorithms using spatial auto-correlation. International Journal of Remote Sensing 27, 3035-3040.
22. García, V., Mollineda, R., Sánchez, J., Alejo, R., Sotoca, J., 2007. When overlap-ping unexpectedly alters the class imbalance effects. In: Martí, J., Benedí, J.,Mendonç a, A., Serrat, J. (Eds.), Lecture Notes in Computer Science. Springer,Berlin/Heidelberg, pp. 499-506.
23. Genuer, R., Michel, V., Eger, E., Thirion, B., 2010. Random Forest based feature selec-tion for decoding fMRI data. In: Proceeding of the 19th COMPSTAT, Paris, France,pp. 1079-1087.
24. Gislason, P.O., Benediktsson, J.A., Sveinsson, J.R., 2006. Random forests for land coverclassification. Pattern Recognition Letters 27, 294-300
25. Guo, L., Chehata, N., Mallet, C., Boukir, S., 2011. Relevance of airborne lidar and mul-tispectral image data for urban scene classification using Random Forests. ISPRSInternational Journal of Photogrammetry and Remote Sensing 66, 56-66
26. He, H., Garcia, E.A., 2009. Learning from imbalanced data. IEEE Transactions onKnowledge and Data Engineering 21, 1263-1284.
27. Hubert-Moy, L., Nabucet, J., Lecerf, R., Dufour, S., Burel, F., 2012. Green and blue beltnetworks: mapping connectivity areas at a regional scale using medium andhigh spatial resolution satellite images. In: IEEE International Geoscience andRemote Sensing Symposium IGARSS 2012, pp. 6095-6098.
28. IGN, 2012. Données - Services - Prestations de l'Institut national de l'Informationgéographique et forstière, 57p.
29. Iovan, C., Boldo, D., Cord, M., 2008 September. Detection, characterization andmodeling vegetation in urban areas from high resolution aerial imagery. IEEEJournal of Selected Topics in Applied Earth Observations and Remote Sensing 1,206-213.
30. Jongman, R.H.G., Külvik, M., Kristiansen, I., 2004. European ecological networks andgreenways. Landscape and Urban Planning 68, 305-319.
31. Johnson, B., Xie, Z., 2011. Unsupervised image segmentation evaluation and refine-ment using a multi-scale approach. ISPRS Journal of Photogrammetry andRemote Sensing 66, 473-483.
32. Ke, C.Q., Xia, L., Tang, G.D., Cao, X., 2008. Detecting urban vegetation using a object-oriented method with QuickBird imagery. In: IEEE International Geoscience andRemote Sensing Symposium IGARSS 2008, vol. 3, pp. 138-141
33. Key, T., Warne, T.A., McGraw, J.B., Fajvan, M.A., 2001. A comparison of multispectraland multitemporal information in high spatial resolution imagery for classifica-tion of individual tree species in a temperate hardwood forest. Remote Sensingof Environment 75, 100-112.
34. Lang, S., Jekel, T., Hölbling, D., Schöpfer, E., Prinz, T., Kloyber, E., Blaschke, T., 2006.Where the grass is greener - mapping of urban green structures according torelative importance in the eyes of the citizens. In: 1st EARSeL Workshop of theSIG Urban Remote Sensing, Berlin, Germany, pp. 1-8
35. Lawrence, R.L., Wood, S.D., Sheley, R.L., 2006. Mapping invasive plants using hyper-spectral imagery and Breiman Cutler classifications (randomForest). RemoteSensing of Environment 100, 356-362
36. Li, C., Yin, J., Zhao, J., 2010. Extraction of urban vegetation from high resolutionremote sensing image. In: IEEE International Conference on Computer Designand Application, ICCDA 2010, vol. 4, pp. 403-406
37. Liaw, A., Wiener, M., 2002. Classification and Regression by random forest. R News2, 18-22.
38. Martha, T.R., Kerle, N., van Westen, C.J., Jetten, V., Kumar, K.V., 2011. Segment opti-mization and data-driven thresholding for knowledge-based landslide detectionby object-based image analysis. IEEE Transactions on Geoscience and RemoteSensing 49, 4928-4943.
39. Mathieu, R., Freeman, C., Aryal, J., 2007. Mapping private gardens in urban areasusing object-oriented techniques and very high-resolution satellite imagery.Landscape and Urban Planning 81, 179-192.
40. McDonnell, M.J., Hahs, A.K., 2008. The use of gradient analysis studies in advancingour understanding of the ecology of urbanizing landscapes: current status andfuture directions. Landscape Ecology 23, 1143-1155.
41. Nichol, J., Wong, M.S., 2007. Remote sensing of urban vegetation life form by spectralmixture analysis of high-resolution Ikonos satellite images. International Journalof Remote Sensing 28, 985-1000.
42. Pal, M., 2005. Random forest classifier for remote sensing classification. InternationalJournal of Remote Sensing 26, 217-222
43. Pal, N.R., Pal, S.K., 1993. A review on image segmentation techniques. Pattern Recog-nition 29, 1277-1294.
44. Pan, S.J., Yang, Q., 2010. A survey on transfer learning. IEEE Transactions on Knowl-edge and Data Engineering 22, 1345-1359.
45. Peters, J., Van Coillie, F., Westra, T., De Wulf, R., 2011. Synergy of very high resolu-tion optical and radar data for object-based olive grove mapping. InternationalJournal of Geographical Information Science 25, 971-989.
46. Peterson, J., Pussa, K., Liira, J., 2004. Issues related to delineation of forest boundarieson Landsat Thematic Mapper winter images. International Journal of RemoteSensing 25, 5617-5628.
47. Pham, T.T.H., He, D.C., 2008. How do people perceive the city's green space? A viewfrom satellite imagery (in Hanoi, Vietnam). In: IEEE International Geoscienceand Remote Sensing Symposium, IGARSS 2008, vol. 3, pp. 1228-1231.
48. Pham, T.T.H., Apparicio, P., Séguin, A.M., Gagnon, M., 2011. Mapping the greenscapeand environmental equity in Montreal: an application of remote sensing andGIS. In: Caquart, S.B., Vaughan, L., Cartwright, W. (Eds.), Mapping EnvironmentalIssues in the City: Arts and Cartography Cross Perspectives. Springer-Verlag,Berlin, pp. 30-48.
49. Prasad, A.M., Iverson, L.R., Liaw, A., 2006. Newer classification and regression treetechniques: bagging and random forests for ecological prediction. Ecosystems9, 181-199.
50. Qi, J., Chehbouni, A., Huete, A., Kerr, Y., Sorooshian, S., 1994. Modified soiladjusted vegetation index (MSAVI). Remote Sensing of Environment 48,119-126.
51. R Development Core Team, 2012. R: A language and environment for statisticalcomputing. R Foundation for Statistical Computing, Vienna, Austria.
52. Rodriguez-Galiano, V.F., Ghimire, B., Rogan, J., Chica-Olmo, M., Rigol-Sanchez, J.P.,2012. An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing 67,93-104.
53. Schöpfer, E., Lang, S., Blaschke, T., 2005. A "green index" incorporating remotesensing and citizen's perception of green space. International Archives of Pho-togrammetry. Remote Sensing and Spatial Information Sciences, 1-6.
54. Sheeren, D., Bastin, N., Ouin, A., Balent, G., Lacombe, J.P., 2009. Discriminatingsmall wooded elements in rural landscape from aerial photography: a hybridpixel/object-based analysis approach. International Journal of Remote Sensing30, 4979-4990.
55. Smith, A., 2010. Image segmentation scale parameter optimization and land coverclassification using the random forest algorithm. Journal of Spatial Science 55,69-79.
56. Stumpf, A., Kerle, N., 2011. Object-oriented mapping of landslides using randomforests. Remote Sensing of Environment 115, 2564-2577.
57. Stumpf, A., Lachiche, N., Malet, J.-P., Kerle, N., Puissant, A., 2013. Active learning inthe spatial domain for remote sensing image classification. IEEE Transactions onGeoscience and Remote Sensing, http://dx.doi.org/10.1109/TGRS.2013.2262052(in press).
58. Svetnik, V., Liaw, A., Tong, C., Wang, T., 2004. Application of Breiman's random forestto modeling structure-activity relationships of pharmaceutical molecules. In:Roli, F., Kittler, J., Windeatt, T. (Eds.), Multiple Classifier Systems. Springer, Berlin,pp. 334-343.
59. Tan, Q., Wang, J., 2009. Mapping urban tree coverage using object-oriented imageanalysis method: a case study. In: IEEE International Geoscience and RemoteSensing Symposium, IGARSS 2009, vol. 5, pp. 342-345.
60. Tooke, T.R., Coops, N.C., et al., 2009. Extracting urban vegetation characteristics usingspectral mixture analysis and decision tree classifications. Remote Sensing ofEnvironment 113 (2), 398-407.
61. Tuia, D., Volpi, M., Copa, L., Kanevski, M., Munoz-Mari, J., 2011. A survey of activelearning algorithms for supervised remote sensing image classification. IEEEJournal of Selected Topics in Signal Processing 5, 606-617.
62. Tuominen, S., Pekkarinen, A., 2005. Performance of different spectral and texturalaerial photograph features in multi-source forest inventory. Remote Sensing ofEnvironment 94, 256-268.
63. Van Delm, A., Gulinck, H., 2011. Classification and quantification of green in theexpanding urban and semi-urban complex: application of detailed field dataand Ikonos-imagery. Ecological Indicators 11, 52-60.
64. Vannier, C., Hubert-Moy, L., 2010. Wooded hedgerows characterization inrural landscapes using very high spatial resolution satellite images. IEEEInternational Geoscience and Remote Sensing Symposium, IGARSS 2010,347-350.
65. Watts, J.D., Lawrence, L., 2008. Merging Random Forest classification an object-oriented approach for analysis of agricultural lands. International Archives ofthe Photogrammetry, Remote Sensing and Spatial Information Sciences 37 (Part4/B7), 579-582.
66. Youjing, Z., Hengtong, F., 2007. Identification scales for urban vegetation classifica-tion using high spatial resolution satellite data. In: IEEE International Geoscienceand Remote Sensing Symposium, IGARSS 2007, pp. 1472-1475.
67. Zhang, X., Feng, X., 2005. Detecting urban vegetation from Ikonos data usingan object-oriented approach. Proceedings, IEEE International Geoscience andRemote Sensing Symposium, IGARSS'05 2, 1475-1478.
68. Zhang, X., Feng, X., Jiang, H., 2010. Object-oriented method for urban vegetationmapping using Ikonos imagery. International Journal of Remote Sensing 31,177-196.