Investigating Feature Extraction for Domain Adaptation in Remote Sensing Image Classification

Giona Matasci, Lorenzo Bruzzone, Michele Volpi, Devis Tuia, Mikhail Kanevski

Abstract

In this contribution, we explore the feature extraction framework to ease the knowledge transfer in the thematic classification of multiple remotely sensed images. By projecting the images in a common feature space, the purpose is to statistically align a given target image to another source image of the same type for which we dispose of already collected ground truth. Therefore, a classifier trained on the source image can directly be applied on the target image. We analyze and compare the performance of classic feature extraction techniques and that of a dedicated method issued from the field of domain adaptation. We also test the influence of different setups of the problem, namely the application of histogram matching and the origin of the samples used to compute the projections. Experiments on multi- and hyper-spectral images reveal the benefits of the feature extraction step and highlight insightful properties of the different adopted strategies.

References

  1. Arenas-García, J. and Petersen, K. B. (2009). Kernel multivariate analysis in remote sensing feature extraction. In Camps-Valls, G. and Bruzzone, L., editors, Kernel Methods for Remote Sensing Data Analysis. J. Wiley & Sons, NJ, USA.
  2. Borgwardt, K. M., Gretton, A., Rasch, M. J., Kriegel, H.-P., Schölkopf, B., and Smola, A. J. (2006). Integrating structured biological data by Kernel Maximum Mean Discrepancy. Bioinformatics, 22(14):e49-e57.
  3. Bruzzone, L. and Persello, C. (2009). A novel approach to the selection of spatially invariant features for the classification of hyperspectral images with improved generalization capability. IEEE Trans. Geosci. Remote Sens., 47(9):3180-3191.
  4. Bruzzone, L. and Prieto, D. F. (2001). Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images. IEEE Trans. Geosci. Remote Sens., 39(2):456-460.
  5. Inamdar, S., Bovolo, F., and Bruzzone, L. (2008). Multidimensional probability density function matching for preprocessing of multitemporal remote sensing images. IEEE Trans. Geosci. Remote Sens., 46(4):1243- 1252.
  6. Nielsen, A. A., Conradsen, K., and Simpson, J. J. (1998). Multivariate alteration detection (MAD) and MAF postprocessing in multispectral, bitemporal image data: New approaches to change detection studies. Remote Sens. Environ., 64:1-19.
  7. Pan, S. J., Tsang, I., Kwok, J. T., and Yang, Q. (2011). Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw., 22(2):199-210.
  8. Pan, S. J. and Yang, Q. (2010). A survey on transfer learning. IEEE Trans. Knowl. Data Eng., 22(10):1345- 1359.
  9. Schölkopf, B., Smola, A., and Müller, K.-R. (1998). Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput., 10(5):1299-1319.
  10. Tuia, D., Mun˜oz-Marí, J., Gomez-Chova, L., and Malo, J. (2012). Graph matching for adaptation in remote sensing. IEEE Trans. Geosci. Remote Sens., PP(99):1-13.
  11. Woodcock, C. E., Macomber, S. A., Pax-Lenney, M., and Cohen, W. B. (2001). Monitoring large areas for forest change using Landsat: Generalization across space, time and Landsat sensors. Remote Sens. Environ., 78(1-2):194-203.
Download


Paper Citation


in Harvard Style

Matasci G., Bruzzone L., Volpi M., Tuia D. and Kanevski M. (2013). Investigating Feature Extraction for Domain Adaptation in Remote Sensing Image Classification . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 419-424. DOI: 10.5220/0004199504190424


in Bibtex Style

@conference{icpram13,
author={Giona Matasci and Lorenzo Bruzzone and Michele Volpi and Devis Tuia and Mikhail Kanevski},
title={Investigating Feature Extraction for Domain Adaptation in Remote Sensing Image Classification},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={419-424},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004199504190424},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Investigating Feature Extraction for Domain Adaptation in Remote Sensing Image Classification
SN - 978-989-8565-41-9
AU - Matasci G.
AU - Bruzzone L.
AU - Volpi M.
AU - Tuia D.
AU - Kanevski M.
PY - 2013
SP - 419
EP - 424
DO - 10.5220/0004199504190424