Publicado

2017-01-01

A comparative study of multiscale representations for spatialspectral classification of hyperspectral imagery

Estudio comparativo de representaciones multiescala para clasificación de imágenes hiperespectrales

Palabras clave:

nonlinear diffusion, binary partition tree, classification, hyperspectral imagery, multiscale representation, remote sensing (en)
difusión no lineal, árbol de partición binaria, clasificación, imagen hiperespectral, representación multiescala, percepción remota (es)

Autores/as

Hyperspectral remote sensors acquire data coming from hundreds of narrow bands through the electromagnetic spectrum; this allows the terrestrial and maritime surfaces to be characterized for Earth observation. Hyperspectral image processing requires algorithms that combine spatial and spectral information. One way to take full advantage of spatial-spectral data within hyperspectral imagery is to use multiscale representations. A multiscale representation generates a family of images were fine details are systematically removed. This paper compares two multiscale representation approaches in order to improve the classification of hyperspectral imagery. The first approach is based on nonlinear diffusion, which obtains a multiscale representation by successive filtering. The second is based on binary partition tree, an approach inspired in region growing. The comparison is performed using a real hyperspectral image and a supper vector machine classifier. Both representation approaches allowed the classification of hyperspectral imagery to be improved. However, nonlinear diffusion results surpassed those obtained using binary partition tree.
Los sensores remotos hiperespectrales adquieren datos a lo largo de cientos de bandas estrechas a través del espectro electromagnético permitiendo la caracterización de las superficies terrestres y marítimas para la observación de la Tierra. El procesamiento de imágenes hiperespectrales requiere de algoritmos que combinen la información espacial y espectral. Una forma de tomar ventaja de los datos espaciales y espectrales en las imágenes hiperespectrales es usar representaciones multiescala. Una representación multiescala genera una familia de imágenes donde los detalles finos son sistemáticamente removidos. Este artículo compara dos enfoques de representación multiescala para mejorar la clasificación de imágenes hiperespectrales. El primer enfoque se base en difusión no linear la cual obtiene la representación multiescala por medio de sucesivos filtros. El segundo se basa en un árbol de partición binaria, un enfoque inspirado en crecimiento de regiones. La comparación se realiza usando la imagen hiperespectral Indian Pines y un clasificador de máquinas de soporte vectorial. Ambos enfoques de representación permiten mejorar la clasificación de la imagen hiperespectral. Pero, los resultados de difusión no lineal superan los obtenidos usando el árbol de partición binaria.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Richards, J.A. and Xia, J., Remote sensing digital image analysis: An introduction. 5th edition. Springer, 2013.

Plaza, A., Benediktsson, J., Boardman, J., Brazile, J., Bruzzone, L., Camps-Valls, G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., Marconcini, M., Tilton, J. and Trianni, G., Recent advances in techniques for hyperspectral image processing. Remote Sensing of Environment, 113, pp. s110–s122, 2009. DOI: 10.1016/j.rse.2007.07.028

Blaschke, T., Object based image analysis for remote sensing. Journal of Photogrammetry and Remote Sensing, 65, pp. 2-16, 2010. DOI: 10.1016/j.isprsjprs.2009.06.004

Jimenez, L., Rivera-Medina, J., Rodriguez-Diaz, E., Arzuaga-Cruz, E. and Ramirez-Velez, M., Integration of spatial and spectral information by means of unsupervised extraction and classification for homogeneous objects applied to multispectral and hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 43(4), pp. 844-851, 2005. DOI: 10.1109/TGRS.2004.843193

Tilton, J.C., Image segmentation by region growing and spectral clustering with a natural convergence criterion. IEEE Geoscience & Remote Sensing Symposium, 1998. pp. 1766-1768.

Tarabalka, Y., Benediktsson, J.A., Chanussot, J. and Tilton, J.C., Multiple spectral–spatial classification approach for hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 48(11), pp. 4122-4132, 2010. DOI: 10.1109/TGRS.2010.2062526

Li, J., Bioucas-Dias, J.M. and Plaza, A., Spectral–spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields. IEEE Transactions on Geoscience and Remote Sensing, 50(3), pp. 809-823, 2012. DOI: 10.1109/TGRS.2011.2162649

Lindeberg, T., Scale-space theory in computer vision. Kluwer Academic Publisher, 1994.

Duarte, J.M., Castillo, P. and Velez-Reyes, M., Comparative study of semiimplicit schemes for onlinear diffusion in hyperspectral imagery. IEEE Transactions on Image Processing, 16(5), pp. 1303-1314, 2007. DOI: 10.1109/TIP.2007.894266

Duarte, J.M., Sapiro, G., Velez, M. and Castilo, P., Multiscale representation and segmentation of hyperspectral imagery using geometric partial differential equations and algebraic multigrid methods. IEEE Transactions on Geosciences and Remote Sensing, 46(8), pp. 1303-1314, 2008. DOI: 10.1109/TGRS.2008.916478

Torres-Madronero, M.C. and Velez-Reyes, M., Integrating spatial information in unsupervised unmixing of hyperspectral imagery using multiscale representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6), pp. 1985-1993, 2014. DOI: 10.1109/JSTARS.2014.2319261

Salembier, P. and Garrido, L., Binary partition tree as an efficient representation for image processing, segmentation and information retrieval. IEEE Transactions on Image Processing, 9(4), pp. 561-576, 2000. DOI: 10.1109/83.841934

Valero, S., Salembier, P. and Chanussot, J., Hyperspectral image representation and processing with binary partition trees. IEEE Transactions on image processing, 22(4), pp. 1430-1443, 2013. DOI: 10.1109/TIP.2012.2231687

Drumetz, L., Veganzones, M.A., Marrero, R., Tochon, G., Dalla, M., Plaza, A. and Chanussot, J., Binary partition tree-based local spectral unmixing. International IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing 2 WHISPERS. 2014.

Weickert, J., Romenu, B. and Viergever, M., Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Transactions on Image Processing, 7(3), pp. 398-410, 1998. DOI: 10.1109/83.661190

Sporring, J. and Weickert, J., Information measures in scale spaces. IEEE Transactions on Information Theory, 45, pp. 1051-1058, 1999. DOI: 10.1109/18.761342

Mrazek, P. and Navarra, M., Selection of optimal stopping time for nonlinear diffusion filtering. International Journal of Computer Vision, 52, pp. 189-203, 2003.

Jiabin, Y. and Guizhong, L., A novel anisotropic diffusion time estimation method. Congress on Image and Signal Processing, 2008. pp. 241-244.