Active learning in the spatial domain for remote sensing image classification

IEEE Transactions on Geoscience and Remote Sensing

Volumn 52, Issue 5, 2014, Pages 2492-2507

  Stumpf, Andre ^a,b   Lachiche, Nicolas ^b   Malet, Jean Philippe ^b   Kerle, Norman ^c   Puissant, Anne ^a  

^a UNIVERSITÉ DE STRASBOURG   (France)

^b UNIVERSITÉ DE STRASBOURG   (France)

^c UNIVERSITY OF TWENTE   (Netherlands)

Author keywords

Active learning (AL); batch mode; class imbalance; ground truth uncertainty; image classification; landslide inventory mapping; spatial information

Indexed keywords

ALGORITHMS; IMAGE RECONSTRUCTION; IMAGE SEGMENTATION; LANDSLIDES; REMOTE SENSING;

ACTIVE LEARNING; BATCH-MODE; CLASS IMBALANCE; GROUND TRUTH; LANDSLIDE INVENTORIES; SPATIAL INFORMATIONS;

IMAGE CLASSIFICATION;

ALGORITHM; ERROR ANALYSIS; HEURISTICS; IMAGE CLASSIFICATION; LANDSLIDE; REMOTE SENSING; SATELLITE IMAGERY; UNCERTAINTY ANALYSIS;

EID: 84898598578     PISSN: 01962892     EISSN: None     Source Type: Journal    
DOI: 10.1109/TGRS.2013.2262052     Document Type: Article

References (65)

1. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning-Data Mining, Inference, and Prediction. New York, NY, USA: Springer-Verlag, 2009.
2. P. O. Gislason, J. A. Benediktsson, and J. R. Sveinsson, "Random Forests for land cover classification," Pattern Recogn. Lett., vol. 27, no. 4, pp. 294-300, Mar. 2006.
3. G. Camps-Valls and L. Bruzzone, "Kernel-based methods for hyperspectral image classification," IEEE Trans. Geosci. Remote Sens., vol. 43, no. 6, pp. 1351-1362, Jun. 2005. (Pubitemid 40811944)
4. L. Bruzzone and F. Melgani, "Robust multiple estimator systems for the analysis of biophysical parameters from remotely sensed data," IEEE Trans. Geosci. Remote Sens., vol. 43, pp. 159-174, Jan. 2005.
5. G. Camps-Valls, L. Bruzzone, J. L. Rojo-Alvarez, and F. Melgani, "Robust support vector regression for biophysical variable estimation from remotely sensed images," IEEE Geosci. Remote Sens. Lett., vol. 3, no. 3, pp. 339-343, Jul. 2006. (Pubitemid 44150320)
6. G. Camps-Valls, L. Gomez-Chova, J. Munoz-Mari, J. L. Rojo-Alvarez, and M. Martinez-Ramon, "Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection," IEEE Trans. Geosci. Remote Sens., vol. 46, pp. 1822-1835, Jun. 2008. (Pubitemid 351711220)
7. A. Banerjee, P. Burlina, and C. Diehl, "A support vector method for anomaly detection in hyperspectral imagery," IEEE Trans. Geosci. Remote Sens., vol. 44, no. 8, pp. 2282-2291, Aug. 2006. (Pubitemid 44192167)
8. A. Brenning, "Benchmarking classifiers to optimally integrate terrain analysis and multispectral remote sensing in automatic rock glacier detection," Remote Sens. Environ., vol. 113, no. 1, pp. 239-247, Jan. 2009.
9. A. Stumpf and N. Kerle, "Object-oriented mapping of landslides using Random Forests," Remote Sens. Environ., vol. 115, no. 10, pp. 2564-2577, Oct. 2011.
10. D. Cohn, "Active Learning," in Encyclopedia of Machine Learning, C. Sammut and G. Webb, Eds. New York, NY, USA: Springer-Verlag, 2011, pp. 10-14.
11. B. Settles, "Active Learning Literature Survey," Univ. Wisconsin-Madison,Wisconsin,MI, USA, Computer SciencesTech.Rep. 1648, 2010.
12. D. Lewis and W. Gale, "A sequential algorithm for training text classifiers," in Proc. 17th Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval, Dublin, Ireland, 1994, pp. 3-12.
13. G. Schohn and D. Cohn, "Less is more: Active learning with support vectors machines," in Proc. 17th Int. Conf. Mach. Learn., Stanford, CA, 2000, pp. 839-846.
14. H. S. Seung, M. Opper, and H. Sompolinsky, "Query by committee," in Proc. 5th Workshop Comput. Learn. Theory, San Mateo, CA, 1992, pp. 287-294. (Pubitemid 23615454)
15. D. Tuia, M. Volpi, L. Copa, M. Kanevski, and J. Munoz-Mari, "A survey of active learning algorithms for supervised remote sensing image classification," IEEE J. Select. Topics Signal Process., vol. 5, no. 3, pp. 606-616, Jun. 2011.
16. S. Rajan, J. Ghosh, and M. M. Crawford, "An active learning approach to hyperspectral data classification," IEEE Trans. Geosci. Remote Sens., vol. 46, no. 4, pp. 1231-1242, Apr. 2008. (Pubitemid 351459470)
17. D. Tuia, F. Ratle, F. Pacifici, M. F. Kanevski, and W. J. Emery, "Active learning methods for remote sensing image classification," IEEE Trans. Geosci. Remote Sens., vol. 47, no. 7, pp. 2218-2232, Jul. 2009.
18. B. Demir, C. Persello, and L. Bruzzone, "Batch-mode active-learning methods for the interactive classification of remote sensing images," IEEE Trans. Geosci. Remote Sens., vol. 49, no. 3, pp. 1014-1031, Mar. 2011.
19. M. Volpi, D. Tuia, andM. Kanevski, "Memory-based cluster sampling for remote sensing image classification," IEEE Trans. Geosci. Remote Sens., vol. 50, no. 8, pp. 3096-3106, Aug. 2012.
20. B. Settles, "From theories to queries," in Proc. JMLR: Workshop Conf., Sardinia, Italy, 2011, pp. 1-8.
21. B. Settles, M. Craven, and L. Friedland, "Active learning with real annotation costs," in Proc. NIPS Workshop Cost-Sensitive Learn., 2008, pp. 1-10.
22. A. Liu, G. Jun, and J. Gho, "Spatially cost-sensitive active learning," presented at the 9th SIAM Int. Conf. Data Mining Sparks, Sparks, NV, USA, 2009.
23. E. Pasolli, F. Melgani, D. Tuia, F. Pacifici, and W. J. Emery, "Improving active learning methods using spatial information," in IEEE IGARSS, 2011, pp. 3923-3926.
24. J. M. Henderson and A. Hollingworth, "High-level scene perception," Annu. Rev. Psychol., vol. 50, pp. 243-271, Feb. 1999.
25. A. Stumpf, N. Lachiche, J.-P. Malet, N. Kerle, and A. Puissant, "Active learning in the spatial-domain for landslide mapping in remote sensing images," presented at the ALRA: Active Learning Real-world Appl. Workshop ECML-PKDD, Bristol, U.K., 2012.
26. A. J. Joshi, F. Porikli, and N. P. Papanikolopoulos, "Scalable active learning for multiclass image classification," IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 11, pp. 2259-2273, Nov. 2012.
27. T. S. F. Haines and T. Xiang, "Active learning using Dirichlet processes for rare class discovery and classification," in British Machine Vision Conf. Univ. Dundee, Dundee, U.K., 2011.
28. J. Michel, J. Malik, and J. Inglada, "Lazy yet efficient land-cover map generation for HR optical images," in Proc. IEEE IGARSS, 2010, pp. 1863-1866.
29. A. Borisov, E. Tuv, and G. Runger, "Active batch learning with stochastic query-by-forest (SQBF)," in Proc. JMLR Workshop Active Learn. Exp. Des., 2011, pp. 50-69.
30. J. Muñoz-Mar?á, D. Tuia, and G. Camps-Valls, "Semisupervised classification of remote sensing images with active queries," IEEE Trans. Geosci. Remote Sens., vol. 50, no. 10, pp. 3751-3763, Oct. 2012.
31. D. Tuia, J. Muñoz-Marí, and G. Camps-Valls, "Remote sensing image segmentation by active queries," Pattern Recognit., vol. 45, no. 6, pp. 2180-2192, Jun. 2012.
32. B. Demir, L. Minello, and L. Bruzzone, "A cost-sensitive active learning technique for the definition of effective training sets for supervised classifiers," in Proc. IEEE IGARSS, 2012, pp. 1781-1784.
33. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5-32, Oct. 2001. (Pubitemid 32933532)
34. L. Copa, D. Tuia, M. Volpi, and M. Kanevski, "Unbiased query-bybagging active learning for VHR image classification," in Proc. SPIE Remote Sensing Conf., Toulouse, France, 2010, p. 78300K.
35. Z. Xu, K. Yu, V. Tresp, X. Xu, and J. Wang, "Representative sampling for text classification using support vector machines," in Proc. 25th Eur. Conf. Inf. Retrieval Res., Pisa, Italy, 2003, pp. 393-407.
36. S. Boltz, E. Debreuve, and M. Barlaud, "kNN-based high-dimensional Kullback-Leibler distance for tracking," in Proc. 8th Int. WIAMIS, 2007, p. 16.
37. R package version 0.6-3 S. Li, FNN: Fast nearest neighbor search algorithms and applications 2012, R package version 0.6-3.
38. C. Strobl, A.-L. Boulesteix, A. Zeileis, and T. Hothorn, "Bias in random forest variable importance measures: Illustrations, sources and a solution," BMC Bioinformat., vol. 8, p. 25, Jan. 2007.
39. K. Nicodemus, J. Malley, C. Strobl, and A. Ziegler, "The behaviour of random forest permutation-based variable importance measures under predictor correlation," BMC Bioinformat., vol. 11, p. 110, Feb. 2010.
40. A. Verikas, A. Gelzinis, and M. Bacauskiene, "Mining data with random forests: A survey and results of new tests," Pattern Recognit., vol. 44, no. 2, pp. 330-349, Feb. 2011.
41. K. K. Nicodemus, "Letter to the Editor: On the stability and ranking of predictors from random forest variable importance measures," Briefings Bioinformat., vol. 12, no. 4, pp. 369-373, Jul. 1, 2011.
42. W. G. Cochran, Sampling Techniques. NewYork, NY, USA: Wiley, 1977.
43. D. J. J. Walvoort, D. J. Brus, and J. J. de Gruijter, "An R package for spatial coverage sampling and random sampling from compact geographical strata by k-means," Comput. Geosci., vol. 36, no. 10, pp. 1261-1267, Oct. 2010.
44. N. Abe and H. Mamitsuka, "Query learning strategies using boosting and bagging," in Proc. 15th Int. Conf. Mach. Learn., Madison, WI, USA, 1998, pp. 1-9.
45. A. S. Avelar, A. L. C. Netto, W. A. Lacerda, L. B. Becker, and M. B. Mendonça, "Mechanisms of the recent catastrophic landslides in the mountainous range of Rio de Janeiro, Brazil," presented at the 2nd World Landslide Forum, Rome, Italy, 2011.
46. T. Gorum, X. Fan, C. J. van Westen, R. Q. Huang, Q. Xu, C. Tang, and G.Wang, "Distribution pattern of earthquake-induced landslides triggered by the 12 May 2008 Wenchuan earthquake," Geomorphology, vol. 133, no. 3/4, pp. 152-167, Oct. 2011.
47. M. Drusch, U. Del Bello, S. Carlier, O. Colin, V. Fernandez, F. Gascon, B. Hoersch, C. Isola, P. Laberinti, P. Martimort, A. Meygret, F. Spoto, O. Sy, F. Marchese, and P. Bargellini, "Sentinel-2: ESA's optical highresolution mission for GMES operational services," Remote Sens. Environ., vol. 120, pp. 25-36, May 2012.
48. ASTER-GDEM-VALIDATION-TEAM, ASTER global digital elevation model version2-Summaryof validation results,METI/ERSDAC, NASA/LPDAAC, USGS/EROS2011.
49. E. J. Pebesma, "Multivariable geostatistics in S: The gstat package," Comput. Geosci., vol. 30, no. 7, pp. 683-691, Aug. 2004. (Pubitemid 38994762)
50. F. Ardizzone, M. Cardinali, A. Carrara, F. Guzzetti, and P. Reichenbach, "Impact of mapping errors on the reliability of landslide hazard maps," Nat. Hazards Earth Syst. Sci., vol. 2, no. 1/2, pp. 3-14, 2002.
51. M. Galli, F. Ardizzone, M. Cardinali, F. Guzzetti, and P. Reichenbach, "Comparing landslide inventory maps," Geomorphology, vol. 94, no. 3/4, pp. 268-289, Feb. 2008.
52. P. Smyth, "Bounds on the mean classification error rate of multiple experts," Pattern Recognit. Lett., vol. 17, no. 12, pp. 1253-1257, Oct. 1996. (Pubitemid 126384221)
53. T. A. Lampert, A. Stumpf, and P. Gançarski, "An Empirical Study into Annotator Agreement, Ground Truth Estimation, and Algorithm Evaluation," arXiv:1307.0426 [cs.CV], 2013.
54. H. He and E. A. Garcia, "Learning from imbalanced data," IEEE Trans. Know. Data Eng., vol. 21, no. 9, pp. 1263-1284, Sep. 2009.
55. Y. S. Abu-Mostafa, M. Magdon-Ismail, and H.-T. Lin, "Learning from data: A short course," AMLBook, 2012.
56. M. Baatz and A. Schäpe, "Multiresolution Segmentation-An optimization approach for high quality multi-scale image segmentation," presented at the Angewandte Geographische Informationsverarbeitung XII, Salzburg, Austria, 2000.
57. T. R. Martha, N. Kerle, C. J. van Westen, V. Jetten, and K. V. Kumar, "Segment optimization and data-driven thresholding for knowledge-based landslide detection by object-based image analysis," IEEE Trans. Geosci. Remote Sens., vol. 49, no. 12, pp. 4928-4943, Dec. 2011.
58. T. Martha, N. Kerle, C. J. van Westen, and K. Kumar, "Characterising spectral, spatial and morphometric properties of landslides for semiautomatic detection using object-oriented methods," Geomorphology, vol. 116, no. 1/2, pp. 24-36, Mar. 2010.
59. S. K. Jenson and J. O. Domingue, "Extracting topographic structure from digital elevation data for geographic information system analysis," Photgramm. Eng. Remote Sens., vol. 54, no. 11, pp. 1593-1600, 1988.
60. T. K. Tesfa, D. G. Tarboton, D. W. Watson, K. A. T. Schreuders, M. E. Baker, and R. M. Wallace, "Extraction of hydrological proximity measures from DEMs using parallel processing," Environ. Modell. Softw., vol. 26, no. 12, pp. 1696-1709, Dec. 2011.
61. eCognition Developer 8.64.0 Reference Book, Trimble, München, Germany, 2011, Trimble Documentation.
62. J. Southworth, "An assessment of Landsat TM band 6 thermal data for analysing land cover in tropical dry forest regions," Int. J. Remote Sens., vol. 25, no. 4, pp. 689-706, Feb. 2004. (Pubitemid 38329661)
63. C. Chen, A. Liaw, and L. Breiman, "Using random forest to learn imbalanced data," Dept. Statistics, Unive. California, Berkeley, CA, USA, 2004.
64. V. García, R. Mollineda, J. Sánchez, R. Alejo, and J. Sotoca, When Overlapping Unexpectedly Alters the Class Imbalance Effects, J. Martí, J. Benedí, A. Mendonça, and J. Serrat, Eds. Berlin, Gemany: Springer-Verlag, 2007, pp. 499-506.
65. G. M. Foody, "Assessing the accuracy of land cover change with imperfect ground reference data," Remote Sens. Environ., vol. 114, no. 10, pp. 2271-2285, Oct. 2010.