Abstract
Change detection is an important problem in the analysis of optical remote sensing images. The usual way of approaching this problem is by thresholding a difference image in order to obtain a detection mask, but the choice of this threshold is not always easy as the distribution of the values of changed and unchanged pixels may overlap. Therefore, an automatic detector can lead to a high number of false alarms. In this paper, we propose to improve this technique by designing a nonlinear filtering step that highlights the changes in the difference image. In order to better accomplish this process, a previous segmentation stage using texture information from the original images is required. This information can also be used to dismiss areas that do not contain changes with a high likelihood. We show that the process separates the distribution of values in the changed region from the unchanged region and make the choice of the threshold more robust. This results in a significantly lower error than obtaining the mask from the difference image without previous nonlinear filtering. The proposed technique has been used with success in the detection of new constructions on non-urban soil from very-high-resolution aerial images.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig7_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig8_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig9_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig10_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig11_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-014-0690-z/MediaObjects/11760_2014_690_Fig12_HTML.jpg)
Similar content being viewed by others
References
Singh, A.: Digital change detection techniques using remotely-sensed data. Int. J. Remote Sens. 10, 989–1003 (1989)
Bruzzone, L., Prieto, D.: Automatic analysis of the difference image for unsupervised change detection. IEEE Trans. Geosci. Remote Sens. 38, 1171–1182 (2000)
Bobolo, F., Bruzzone, L., Marconcini, M.: A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure. IEEE Trans. Geosci. Remote Sens. 46, 2070–2082 (2008)
Celik, T.: Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geosci. Remote Sens. Lett. 6, 772–776 (2009)
Bovolo, F., Bruzzone, L.: A detail-preserving scale-driven approach to change detection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens. 43, 2963–2972 (2005)
Celik, T., Ma, K.: Unsupervised change detection for satellite images using dual-tree complex wavelet transform. IEEE Trans. Geosci. Remote Sens. 48, 1199–1210 (2010)
Stringa, E.: Morphological change detection algorithms for surveillance applications. In: Proceedings of British Machine Vision Conference, pp. 1–10 (2000)
Kasetkasem, T., Varshney, P.: An image change detection algorithm based on markov random field models. IEEE Trans. Geosci. Remote Sens. 40, 1815–1823 (2002)
Benedek, C., Sziranyi, T.: Change detection in optical aerial images by a multilayer conditional mixed Markov model. IEEE Trans. Geosci. Remote Sens. 47, 3416–3430 (2009)
Dianat, R., Kasaei, S.: Change detection in optical remote sensing images using difference-based methods and spatial information. IEEE Geosci. Remote Sens. Lett. 7, 215–219 (2010)
Bouchiha, R., Besbes, K.: Comparison of local descriptors for automatic remote sensing image registration. Signal Image Video Processing, pp. 1–7 (2013)
Xu, T., Gondra, I.: A simple and effective texture characterization for image segmentation. Signal Image Video Process. 6(2), 231–245 (2012)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley-Interscience, London (2000)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice-Hall, Upper Saddle River, NJ (2006)
Vergara, L., Bernabeu, O.: Simple approach to nonlinear prediction. Electron. Lett. 37, 928–936 (2001)
Acknowledgments
This work has been supported by the Valencian Cartographic Institute under a research and development project and by the Generalitat Valenciana under Grant No. PROMETEO/2010/040.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bosch, I., Serrano, A., Vergara, L. et al. Change detection with texture segmentation and nonlinear filtering in optical remote sensing images. SIViP 9, 1955–1963 (2015). https://doi.org/10.1007/s11760-014-0690-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-014-0690-z