Performance assessment of a recent change detection method for homogeneous and heterogeneous images

  • Jorge Prendes TéSA Laboratory, 7 boulevard de la Gare, 31500 Toulouse, France
  • Marie Chabert University of Toulouse, INP/ENSEEIHT - IRIT, 2 rue Charles Camichel, 31071 Toulouse Cedex 7, France
  • Frédéric Pascal Supélec - SONDRA, Plateau du Moulon, 3 rue Joliot-Curie, F-91192 Gif-sur-Yvette Cedex, France
  • Alain Giros CNES, 18 Av. Edouard Belin, 31401 Toulouse, France
  • Jean-Yves Tourneret University of Toulouse, INP/ENSEEIHT - IRIT, 2 rue Charles Camichel, 31071 Toulouse Cedex 7, France

Résumé

A statistical model for detecting changes in remote sensing images has recently been proposed in (Prendes et al., 2014a,b). This model is sufficiently general to be used for homogeneous images acquired by the same kind of sensors (e.g., two optical images from Pléiades satellites, possibly with different acquisition conditions), and for heterogeneous images acquired by different sensors (e.g., an optical image acquired from a Pléiades satellite and a synthetic aperture radar (SAR) image acquired from a TerraSAR-X satellite). This model assumes that each pixel is distributed according to a mixture of distributions depending on the noise properties and on the sensor intensity responses to the actual scene. The parameters of the resulting statistical model can be estimated by using the classical expectation-maximization (EM) algorithm. The estimated parameters are finally used to learn the relationships between the images of interest, via a manifold learning strategy. These relationships are relevant for many image processing applications, particularly those requiring a similarity measure (e.g., image change detection and image registration). The main objective of this paper is to evaluate the performance of a change detection method based on this manifold learning strategy initially introduced in (Prendes et al., 2014a,b). This performance is evaluated by using results obtained with pairs of real optical images acquired from Pléiades satellites and pairs of optical and SAR images.

Références

* Carrara, W. G., Goodman, R. S., Majewski, R. M., 1995. Spotlight Synthetic Aperture Radar: Signal Processing Algorithms. Artech House signal processing library. Artech House.
* Curlander, J. C., McDonough, R. N., 1991. Synthetic Aperture Radar: Systems and Signal Processing. Wiley Series in Remote Sensing and Image Processing. Wiley.
* Figueiredo, M. A. T., Jain, A. K., March 2002. Unsupervised learning of finite mixture models. IEEE Trans. Pattern Anal. Mach. Intell. 24 (3), 381–396.
* Mercier, G., Moser, G., Serpico, S. B., May 2008. Conditional copulas for change detection in heterogeneous remote sensing images. IEEE Trans. Geosci. and Remote Sensing 46 (5), 1428–1441.
* Peterson, W. W., Birdsall, T., Fox, W., Sept. 1954. The theory of signal detectability. IRE Trans. Inf. Theory 4 (4), 171–212.
* Poulain, V., Inglada, J., Spigai, M., Tourneret, J.-Y., Marthon, P., 2010. High resolution optical and SAR image fusion for road database updating. In: Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS). Honolulu, USA, pp. 2747–2750.
* Prendes, J., Chabert, M., Pascal, F., Giros, A., Tourneret, J.-Y., May 2014. A multivariate statistical model for multiple images acquired by homogeneous or heterogeneous sensors. In: Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc. Florence, Italy.
* Prendes, J., Chabert, M., Pascal, F., Giros, A., Tourneret, J.-Y., 2015. A new multivariate statistical model for change detection in images acquired by homogeneous and heterogeneous sensors. To appear in IEEE Trans. Image Process.
* Schowengerdt, R., 2006. Remote Sensing: Models and Methods for Image Processing. Elsevier Science.
* Storie, C. D., Storie, J., Salinas de Salmuni, G., 2012. Urban boundary extraction using 2-component polarimetric SAR decomposition. In: Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS). Munich, Germany, pp. 5741–5744.
* Thomas, C., Ranchin, T., Wald, L., Chanussot, J., May 2008. Synthesis of multispectral images to high spatial resolution: A critical review of fusion methods based on remote sensing physics. IEEE Trans. Geosci. and Remote Sensing 46 (5), 1301–1312.
* Tison, C., Nicolas, J.-M., Tupin, F., Maitre, H., Oct. 2004. A new statistical model for markovian classification of urban areas in high-resolution SAR images. IEEE Trans. Geosci. and Remote Sensing 42 (10), 2046–2057.
* Uprety, P., Yamazaki, F., 2012. Use of high-resolution SAR intensity images for damage detection from the 2010 Haiti earthquake. In: Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS). Munich, Germany, pp. 6829–6832.
Publiée
2015-01-29
Comment citer
PRENDES, Jorge et al. Performance assessment of a recent change detection method for homogeneous and heterogeneous images. Revue Française de Photogrammétrie et de Télédétection, [S.l.], n. 209, p. 23-29, jan. 2015. ISSN 1768-9791. Disponible à l'adresse : >https://www.sfpt.fr/rfpt/index.php/RFPT/article/view/216>. Date de consultation : 22 nov. 2017
Rubrique
Articles

Mots-clés

Remote sensing, heterogeneous images, Pléiades, SAR, change detection, similarity measure, mixture models