Abstract
The availability of remote sensing images with high spectral, spatial and temporal resolutions has motivated the design of new change detection (CD) methods for surveying changes in a studied area. The challenge of unsupervised CD is to develop flexible automatic models to estimate changes. In this paper, we propose a novel hierarchical Bayesian model for CD. Our main contribution lies in the application of Bernoulli-based models to change detection and transforming it to a denoising problem. The originality is related to the capacity of these models to act as implicit classifiers in addition to the denoising effect since even for changed pixels noise is also removed. The second originality lies in the way inference is conducted. Specifically, the hierarchical Bayesian model and Gibbs sampler ensure building an algorithm with secure convergence guarantees. Experiments performed on real data indicate the benefit that can be drawn from our approach.
Similar content being viewed by others
Notes
A commercial Earth observation satellite, owned by DigitalGlobe: https://www.digitalglobe.com/resources/satellite-information.
References
Ashbindu, S.: Digital change detection techniques using remotely-sensed data. Int. J. Remote Sens. 10(6), 989–1003 (1989)
Baisantry, M., Negi, D.S., Manocha, O.P.: Change vector analysis using enhanced PCA and inverse triangular function-based thresholding. Def. Sci. J. 62(4), 236–242 (2012)
Bovolo, F., Bruzzone, L.: A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain. IEEE Trans. Geosci. Remote Sens. 45(1), 218–236 (2007)
Bovolo, F., Marchesi, S., Bruzzone, L.: A framework for automatic and unsupervised detection of multiple changes in multitemporal images. IEEE Trans. Geosci. Remote Sens. 50(6), 2196–2212 (2012)
Bruzzone, L., Bovolo, F.: A novel framework for the design of change-detection systems for very-high-resolution remote sensing images. Proc. IEEE 101(3), 609–630 (2013)
Bruzzone, L., Prieto, D.F.: Automatic analysis of the difference image for unsupervised change detection. IEEE Trans. Geosci. Remote Sens. 38(3), 1171–1182 (2000)
Chaari, L., Pesquet, J.C., Tourneret, J.Y., Ciuciu, P., Benazza-Benyahia, A.: A hierarchical bayesian model for frame representation. IEEE Trans. Signal Process. 58(11), 5560–5571 (2010)
Chaari, L., Tourneret, J.Y., Batatia, H.: Sparse Bayesian regularization using Bernoulli–Laplacian priors. In: Signal Process. Conference, pp. 1–5. IEEE (2013)
Chen, G., Hay, G.J.: An airborne lidar sampling strategy to model forest canopy height from quickbird imagery and geobia. Remote Sens. Environ. 115(6), 1532–1542 (2011)
Chen, M.D.H.D.: Segmentation for object-based image analysis: a review of algorithms and challenges from remote sensing perspective. J. Photogramm. Remote Sens. 150, 115–134 (2019)
Coppin, P., Jonckheere, I., Lambin, E.: Digital change detection methods in ecosystem monitoring: a review. Int. J. Remote Sens. 25, 1565–1596 (2004)
Dobigeon, N., Hero, A.O., Tourneret, J.Y.: Hierarchical Bayesian sparse image reconstruction with application to MRFM. IEEE Trans. Image Process. 18(9), 2059–2070 (2009)
Krylov, V.A., Moser, G., Serpico, S.B., Zerubia, J.: False discovery rate approach to unsupervised image change detection. IEEE Trans. Image Process. 25(10), 4704–4718 (2016)
Kwan, C. et al.: Change detection using original and fused landsat and worldview images. In: Proceedings of the IEEE Ubiquitous Computing, Electronics & Mobile Communication Conference, New York, NY, USA, pp. 10–12 (2019)
Kwan, C., et al.: Simple and effective cloud-and shadow-detection algorithms for landsat and worldview images. Signal Image Video Process. 14(1), 125–133 (2020)
Lebedev, M.A., et al.: Change detection in remote sensing images using conditional adversarial networks. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. (2018). https://doi.org/10.5194/isprs-archives-XLII-2-565-2018
Liu, G., Delon, J., Gousseau, Y., Tupin, F.: Unsupervised change detection between multi-sensor high resolution satellite images. In: EUSIPCO, pp. 2435–2439. IEEE (2016)
Liu, S., Bovolo, F., Bruzzone, L., Du, P.: Hierarchical unsupervised change detection in multitemporal hyperspectral images. IEEE Trans. Geosci. Remote Sens. 53(1), 244–260 (2015)
Liu, S., Marinelli, D., Bruzzone, L., Bovolo, F.: A review of change detection in multitemporal hyperspectral images: current techniques, applications, and challenges. IEE Trans. Geosci. Remote Sens. Mag. 7(2), 140–158 (2019)
Liu, W., Yang, J., Zhao, J., Yang, L.: A novel method of unsupervised change detection using multi-temporal polsar images. Remote Sens. 9(11), 1135 (2017)
Lu, D.: Change detection techniques. Int. J. Remote Sens. 25(12), 2365–2401 (2004)
Lv, P., Zhong, Y., Zhao, J., Zhang, L.: Unsupervised change detection based on hybrid conditional random field model for high spatial resolution remote sensing imagery. IEEE Trans. Geosci. Remote Sens. 56(7), 4002–4015 (2018)
Prakash, A., Gupta, R.P.: Land-use mapping and change detection in a coal mining area: a case study in the jharia coalfield, India. Int. J. Remote Sens. 19(3), 391–410 (1998)
Pustelnik, N., Benazza-Benhayia, A., Zheng, Y., Pesquet, J.C.: Wavelet-based image deconvolution and reconstruction. Wiley Encyclopedia of Electrical and Electronics Engineering, pp 1–34 (1999)
Réjichi, S., Chaabane, F.: Satellite image time series classification and analysis using an adapted graph labeling. In: 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images, MultiTemp, Annecy, France, July 22–24, pp. 1–4 (2015)
Réjichi, S., Chaabane, F.: Spatio-temporal regions’ similarity framework for VHR satellite image time series analysis. In: IEEE International Geoscience and Remote Sensing Symposium, Fort Worth, TX, USA, July 23–28, pp. 2845–2848 (2017)
Robert, C., Castella, G.: Monte Carlo Statistical Methods. Springer, Berlin (2004)
Sohl, T.L.: Change analysis in the united arab emirates: an investigation of techniques. Photogramm. Eng. Remote Sens. 65(4), 475–484 (1999)
Tiao, G.C., Tan, W.Y.: Bayesian analysis of random-effect models in the analysis of variance. I. Posterior distribution of variance-components. Biometrika 52(1/2), 37–53 (1965)
Volpi, M., et al.: Supervised change detection in VHR images using contextual information and support vector machines. Int. J. Appl. Earth Observ. Geoinf. 20, 77–85 (2013)
Wang, X., et al.: Object-based change detection in urban areas from high spatial resolution images based on multiple features and ensemble learning. Remote Sens. 10(2), 276 (2018)
Zheng, Y., Fraysse, A., Rodet, T.: Efficient variational Bayesian approximation method based on subspace optimization. IEEE Trans. Image Process. 24(2), 681–693 (2015)
Acknowledgements
This work is supported by the Tunisian program “Projets de Recherche Fédérés” of the Ministry of Higher Education and Scientific Research under the project “Supervision Sensitive de lieux Sensibles multi-capteurs : Super-Sense”.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gharbi, W., Chaari, L. & Benazza-Benyahia, A. Unsupervised Bayesian change detection for remotely sensed images. SIViP 15, 205–213 (2021). https://doi.org/10.1007/s11760-020-01738-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-020-01738-9