AUTOMATIC SELECTION OF THE TRAINING SET FOR SEMI-SUPERVISED LAND CLASSIFICATION AND SEGMENTATION OF SATELLITE IMAGES

Olga Rajadell, Pedro García Sevilla

2012

Abstract

Different scenarios can be found in land classification and segmentation of satellite images. First, when prior knowledge is available, the training data is generally selected by randomly picking samples within classes. When no prior knowledge is available the system can pick samples at random among all unlabeled data, which is highly unreliable, and ask the expert to label them or it can rely on the expert collaboration to improve progressively the training data applying an active learning function. We suggest a scheme to tackle the lack of prior knowledge without actively involving the expert, whose collaboration may be expensive. The proposed scheme uses a clustering technique to analyze the feature space and find the most representative samples for being labeled. In this case the expert is just involved in labeling once a reliable training data set for being representative of the features space. Once the training set is labeled by the expert, different classifiers may be built to process the rest of samples. Three different approaches are presented in this paper: the result of the clustering process, a distance based classifier, and support vector machines (SVM).

References

  1. A.Plaza and et al. (2009). Recent advances in techniques for hyperspectral image processing. Remote sensing of environment, 113:110-122.
  2. Arbelaez, P., Maire, M., Fowlkes, C., and Malik, J. (2011). Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33:898-916.
  3. Cheng, Y. (1995). Mean shift, mode seek, and clustering. IEEE Transaction on Pattern Analysis and Machine, 17(8):790 -799.
  4. Comaniciu, D. and Meer, P. (2002). Mean shift: a robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(5):603 -619.
  5. Landgrebe, D. A. (2003). Signal Theory Methods in Multispectral Remote Sensing. Hoboken, NJ: Wiley, 1 edition.
  6. Li, J., Bioucas-Dias, J., and Plaza, A. (2010). Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE TGRS, 48(11):4085 -4098.
  7. Martínez-Usó, A., Pla, F., Sotoca, J., and García-Sevilla, P. (2007). Clustering-based hyperspectral band selection using information measures. IEEE Trans. on Geoscience & Remote Sensing, 45:4158-4171.
  8. Rajadell, O., Dinh, V. C., Duin, R. P., and García-Sevilla, P. (2011). Semi-supervised hyperspectral pixel classification using interactive labeling. In Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2011.
  9. Tuia, D., Ratle, F., Pacifici, F., Kanevski, M., and Emery, W. (2009). Active learning methods for remote sensing image classification. Geoscience and Remote Sensing, IEEE Transactions on, 47(7):2218 -2232.
  10. Y.Tarabalka, J.Chanussot, and J.A.Benediktsson (2010). Segmentation and classification of hyperspectral images using watershed transformation. Patt.Recogn., 43(7):2367-2379.
Download


Paper Citation


in Harvard Style

Rajadell O. and García Sevilla P. (2012). AUTOMATIC SELECTION OF THE TRAINING SET FOR SEMI-SUPERVISED LAND CLASSIFICATION AND SEGMENTATION OF SATELLITE IMAGES . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012) ISBN 978-989-8425-98-0, pages 412-418. DOI: 10.5220/0003855504120418


in Bibtex Style

@conference{prarshia12,
author={Olga Rajadell and Pedro García Sevilla},
title={AUTOMATIC SELECTION OF THE TRAINING SET FOR SEMI-SUPERVISED LAND CLASSIFICATION AND SEGMENTATION OF SATELLITE IMAGES},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012)},
year={2012},
pages={412-418},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003855504120418},
isbn={978-989-8425-98-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012)
TI - AUTOMATIC SELECTION OF THE TRAINING SET FOR SEMI-SUPERVISED LAND CLASSIFICATION AND SEGMENTATION OF SATELLITE IMAGES
SN - 978-989-8425-98-0
AU - Rajadell O.
AU - García Sevilla P.
PY - 2012
SP - 412
EP - 418
DO - 10.5220/0003855504120418