An Ensemble-Based Training Data Refinement for Automatic Crop Discrimination Using WorldView-2 Imagery

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Volumn 8, Issue 10, 2015, Pages 4882-4894

  Chellasamy, Menaka ^a   Ferré, Ty Paul Andrew ^b   Greve, Mogens Humlekrog ^a  

^a AARHUS UNIVERSITY   (Denmark)

^b UNIVERSITY OF ARIZONA   (United States)

Author keywords

Agricultural parcels; crop discrimination; ensemble; neural classifier; training data; WorldView 2

Indexed keywords

AGRICULTURE; CROPS; ITERATIVE METHODS; SAMPLING;

CLASSIFICATION ACCURACY; CLASSIFICATION APPROACH; CLASSIFICATION SCHEME; CLUSTER CENTROIDS; CROP CLASSIFICATION; CROP DISCRIMINATION; MULTI-SPECTRAL IMAGERY; TRAINING SAMPLE SELECTION;

SATELLITE IMAGERY;

ARTIFICIAL NEURAL NETWORK; CROP; IMAGE CLASSIFICATION; MULTISPECTRAL IMAGE; SATELLITE IMAGERY; SUPERVISED LEARNING; WORLDVIEW;

DENMARK;

EID: 84939182624     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2015.2459754     Document Type: Article

References (47)

1. G. Giacinto and F. Roli, "Ensembles of neural networks for soft classification of remote sensing images, " in Proc. Eur. Symp. Intell. Techn., 1997, pp. 20-21.
2. G. Giacinto and F. Roli, "Design of effective neural network ensembles for image classification purposes, " Image Vis. Comput., vol. 19, pp. 699-707, 2001.
3. M. Aitkenhead and I. Aalders, "Automating land cover mapping of Scotland using expert system and knowledge integration methods, " Remote Sens. Environ., vol. 115, pp. 1285-1295, 2011.
4. M. Chellasamy, R. T. Zielinski, and M. H. Greve, "A multi-evidence approach for crop discrimination using multi-temporal WorldView-2 imagery, " IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 7, no. 8, pp. 3491-3501, Aug. 2014.
5. G. M. Foody, "The significance of border training patterns in classification by a feedforward neural network using back propagation learning, " Int. J. Remote Sens., vol. 20, pp. 3549-3562, Jan. 1, 1999.
6. A. O. Ok and Z. Akyurek, "Automatic training site selection for agricultural crop classification: A case study on Karacabey plain, Turkey, " ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 3819, pp. 221-225, 2011.
7. R. Fuller, G. Groom, and A. Jones, "Land cover map of Great Britain. An automated classification of landsat thematic mapper data, " Photogramm. Eng. Remote Sens., vol. 60, no. 5, pp. 553-562, 1994.
8. X. Huang and J. R. Jensen, "A machine-learning approach to automated knowledge-base building for remote sensing image analysis with GIS data, " Photogramm. Eng. Remote Sens., vol. 63, pp. 1185-1193, 1997.
9. D. Chaudhuri, Hybrid Image Classification Technique for Land-Cover Mapping in the Arctic Tundra. North Slope, AK, USA: ProQuest, 2008.
10. V.-E. Neagoe, A.-D. Ciotec, C.-E. Neghina, and G.-E. Strugaru, "New computational intelligence-based techniques for training sample selection/ generation to improve spatial-contextual classification of multispectral remote sensing imagery, " in Proc. WSEAS Int. Conf. Recent Adv. Inf. Sci., 2012.
11. R. Feitosa, M. Meirelles, and P. Blois, "Using linear regression for automation of supervised classification in multitemporal images, " in Proc. 1st Int. Workshop Anal. Multi-Temporal Remote Sens. Images MultiTemp, 2001, vol. 2, pp. 108-115.
12. T. Cazes, R. Feitosa, and G. Mota, "Automatic selection of training samples for multispectral image classification, " Lect. Notes Comput. Sci., vol. 3212, pp. 389-396, 2004.
13. L. A. Ruiz, J. A. Recio, T. Hermosilla, and A. Sarria, "Identification of agricultural and land cover database changes using object-oriented classification techniques, " in Proc. 33rd Int. Symp. Remote Sens. Environ., May 2009, pp. 4-8.
14. T. Büschenfeld and J. Ostermann, "Automatic refinement of training data for classification of satellite imagery, " ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 1-7, pp. 117-122, 2012.
15. Z. Zhen, L. J. Quackenbush, S. V. Stehman, and L. Zhang, "Impact of training and validation sample selection on classification accuracy and accuracy assessment when using reference polygons in object-based classification, " Int. J. Remote Sens., vol. 34, pp. 6914-6930, 2013.
16. M. Arikan, "Parcel based crop mapping through multi-temporal masking classification of Landsat 7 images in Karacabey, Turkey, " in Proc. ISPRS Symp. Istanbul Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., 2004, p. 1085.
17. A. Zimek, R. J. Campello, and J. Sander, "Ensembles for unsupervised outlier detection: Challenges and research questions a position paper, " ACM SIGKDD Explor. Newslett., vol. 15, pp. 11-22, 2014.
18. S. Verbaeten and A. Van Assche, "Ensemble methods for noise elimination in classification problems, " in Multiple Classifier System. New York, NY, USA: Springer, 2003, pp. 317-325.
19. A. Zimek, M. Gaudet, R. J. Campello, and J. Sander, "Subsampling for efficient and effective unsupervised outlier detection ensembles, " in Proc. 19th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2013, pp. 428-436.
20. C. E. Brodley and M. A. Friedl, "Identifying mislabeled training data, " J. Artif. Intell. Res., vol. 11, pp. 131-167, 1999.
21. K. Jia, S. Liang, X. Wei, L. Zhang, Y. Yao, and S. Gao, "Automatic landcover update approach integrating iterative training sample selection and a Markov Random Field model, " Remote Sens. Lett., vol. 5, pp. 148-156, 2014.
22. P. R. Cohen and M. R. Grinberg, "A theory of heuristic reasoning about uncertainty, " AI Mag., vol. 4, p. 17, 1983.
23. C. Ari and S. Aksoy, "Unsupervised classification of remotely sensed images using Gaussian mixture models and particle swarm optimization, " in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), 2010, pp. 1859-1862.
24. X. Bian and X. Zhang, "Clustering-based extraction of near border training samples for classification of remote sensing image, " in Proc. 4th Int. Workshop Adv. Comput. Intell. (IWACI), 2011, pp. 321-324.
25. P. Shrivastava, P. Singh, and G. Shrivastava, "Image classification using SOM and SVM feature extraction, " Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 1, pp. 264-271, 2014.
26. G. A. Carpenter, M. N. Gjaja, S. Gopal, and C. E. Woodcock, "ART neural networks for remote sensing: Vegetation classification from Landsat TM and terrain data, " IEEE Trans. Geosci. Remote Sens., vol. 35, no. 2, pp. 308-325, Mar. 1997.
27. B. F. Pedersen, "Controlling area based subsidies with RS and GIS in the EU, " in Geoinformations for European Wide Integration. Rotterdam, The Netherlands: Mill Press, 2002, pp. 351-356.
28. C. Murthy, P. Raju, and K. Badrinath, "Classification of wheat crop with multi-temporal images: Performance of maximum likelihood and artificial neural networks, " Int. J. Remote Sens., vol. 24, pp. 4871-4890, 2003.
29. G. Maracci and D. Aifadopoulou, "Multi-temporal remote sensing study of spectral signatures of crops in the Thessaloniki test site, " Int. J. Remote Sens., vol. 11, pp. 1609-1615, 1990.
30. B. D. Wardlow, S. L. Egbert, and J. H. Kastens, "Analysis of time-series MODIS 250 m vegetation index data for crop classification in the US Central Great Plains, " Remote Sens. Environ., vol. 108, pp. 290-310, 2007.
31. C. Tarantino, F. Lovergine, G. Pasquariello, M. Adamo, P. Blonda, and V. Tomaselli, 8-Band Image Data Processing of the WorldView-2 Satellite in a Wide Area of Applications. InTech Open Access, 2012, ISBN: 978-953-307-973-8 [Online]. Available: http://www. intechopen. com/books/ earth-observation /8-band-image-data-processing-of-theworldview-2-satellite-in-a-wide-area-of-applications
32. P. Upadhyay, A. Kumar, P. S. Roy, S. K. Ghosh, and I. Gilbert, "Effect on specific crop mapping usingWorldView-2 multispectral add-on bands: Soft classification approach, " J. Appl. Remote Sens., vol. 6, pp. 063524-1-063524-13, 2012.
33. B. F. Pedersen, "The European way of controlling area based subsidies, " in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS'01), 2001, vol. 4, pp. 1639-1641.
34. J.-K. Kamarainen, V. Kyrki, and H. Kalviainen, "Invariance properties of Gabor filter-based features-overview and applications, " IEEE Trans. Image Process., vol. 15, no. 5, pp. 1088-1099, May 2006.
35. V. Kyrki, J.-K. Kamarainen, and H. Kälviäinen, "Simple Gabor feature space for invariant object recognition, " Pattern Recognit. Lett., vol. 25, pp. 311-318, 2004.
36. R. D. Jackson and A. R. Huete, "Interpreting vegetation indices, " Prev. Vet. Med., vol. 11, pp. 185-200, 1991.
37. A. Shamsoddini, J. C. Trinder, and R. Turner, "Quantization of Pinus forest biophysical parameters using WorldView-2, " in Proc. Latin Amer. Geospatial Forum, 2011, p. 11.
38. A. Wolf, "Using WorldView-2 Vis-NIR MSI imagery to support land mapping and feature extraction using normalized difference index ratios, " in Proc. DigitalGlobe 8-Band Res. Challenge, 2010, pp. 1-13.
39. E. S. Koksal, H. Ustrun, H. Ozcan, and A. Gunturk, "Estimating water stressed dwarf green bean pigment concentration through hyperspectral indices, " Pak. J. Bot., vol. 42, pp. 1895-1901, 2010.
40. A. Wolf, "Using WorldView-2 Vis-NIR MSI imagery to support land mapping and feature extraction using normalized difference index ratios, " in Proc. SPIE, 2010, pp. 1-13.
41. R. S. Kumar, C. Menaka, and M. Cutler, "Ann based robust LULC classification technique using spectral, texture and elevation data, " J. Indian Soc. Remote Sens., vol. 41, pp. 477-486, 2013.
42. M. Aitkenhead, S. Flaherty, and M. Cutler, "Evaluating neural networks and evidence pooling for land cover mapping, " Photogramm. Eng. Remote Sens., vol. 74, pp. 1019-1032, 2008.
43. P. S. Adhvaryu and M. Panchal, "A review on diverse ensemble methods for classification, " IOSR J. Comput. Eng., vol. 1, pp. 27-32, 2012.
44. M. Tian, Q. Yang, A. Maier, I. Schasiepen, N. Maass, and M. Elter, "An automatic histogram-based initializing algorithm for K-means clustering in CT, " in Proc. Workshops Bildverarbeitung für die Medizin, 2013, pp. 277-282.
45. P. J. Deer, P. W. Eklund, and B. D. Norman, "A Mahalanobis distance fuzzy classifier, " in Proc. Aust. New Zealand Conf. Intel. Inf. Syst., 1996, pp. 220-223.
46. H. Kalayeh and D. A. Landgrebe, "Predicting the required number of training samples, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 5, no. 6, pp. 664-667, Nov. 1983.
47. G. O. Toolbox, "Matlab R2012a, " Archived MathWorks Documentation, 2012.