Target Segmentation in Scenes with Diverse Background

  • Christina Grönwall
  • Gustav Tolt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)


We propose a target segmentation approach based on sensor data fusion that can deal with the problem of a diverse background. Features from sensor images, including data from a laser scanner and passive sensors (cameras), are analyzed using Gaussian mixture estimation. The approach tackles some of the difficulties with Gaussian mixtures, e.g., selecting the number of initial components and a good description of data in terms of the number of Gaussian components, and determining the relevant features for the current data set. The feature selection quality is analyzed on-line. We propose a criterion that determines the quality of the resulting clusters in terms of their respective spatial distribution. The output from the analysis is used for object-background segmentation. Segmentation examples of surface-laid mines in outdoor scenes are shown.


Feature selection segmentation Gaussian mixture mine detection cluster selection 


  1. 1.
    Letalick, D., et al.: MOMS - Analysis and evaluation of experimental data, Tech. Rep., FOI, FOI-R–2012-SE (2006)Google Scholar
  2. 2.
    Letalick, D., et al.: MOMS - Progress report 2008, Tech. Rep., FOI, FOI-R–2622-SE (2008)Google Scholar
  3. 3.
    Oliver, J., Baxter, R., Wallace, C.: Unsupervised Learning Using MML. In: 13th International Conference on Machine Learning, pp. 364–372 (1996)Google Scholar
  4. 4.
    Dy, J.G., Brodley, C.E.: Feature Selection for Unsupervised Learning. Journal of Machine Learning Research 5, 845–889 (2004)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Figueiredo, M.A.T., Jain, A.K.: Unsupervised Learning of Finite Mixture Models. IEEE Trans. Pattern Analysis and Machine Intelligence 24(3), 381–396 (2002)CrossRefGoogle Scholar
  6. 6.
    Tolt, G., Westberg, D., Grönwall, C.: A sensor fusion method for detection of surface laid mines. In: Swedish Symposium on Image Analysis, pp. 1–4 (2008)Google Scholar
  7. 7.
    Linderhed, A., Sjökvist, S., Nyberg, S., Uppsäll, M., Grönwall, C., Andersson, P., Letalick, D.: Temporal analysis for land mine detection. In: International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 389–394 (2005)Google Scholar
  8. 8.
    Bali, N., Mohammad-Djafari, A.: Bayesian approach with hidden markov modeling and mean field approximation for hyperspectral data analysis. IEEE Trans. Image Processing 17, 217–225 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Jimenez, L.O., Landgrebe, D.A.: Hyperspectral data analysis and supervised feature reduction via projection pursuit. IEEE Trans. Geoscience and Remote Sensing 37, 2653–2667 (1999)CrossRefGoogle Scholar
  10. 10.
    Constantinopoulos, C., Titsias, M.K., Likas, A.: Bayesian feature and model selection for Gaussian mixture models. IEEE Trans. Pattern Analysis and Machine Intelligence 28, 1013–1018 (2006)CrossRefGoogle Scholar
  11. 11.
    Law, M.H.C., Figueiredo, M.A.T., Jain, A.K.: Simultaneous feature selection and clustering using mixture models. IEEE Trans. Pattern Analysis and Machine Intelligence 26, 1154–1166 (2004)CrossRefGoogle Scholar
  12. 12.
    Mao, K.Z.: Identifying critical variables of principal components using unsupervised feature selection. IEEE Trans. Systems, Man and Cybernetics 35, 339–344 (2005)CrossRefGoogle Scholar
  13. 13.
    Fauvel, M., Benediktsson, J.A., Chanussot, J., Sveinsson, J.R.: Spectral and Aptial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geoscience and Remote Sensing 46, 3804–3814 (2008)CrossRefGoogle Scholar
  14. 14.
    Grönwall, C., Tolt, G., Chevalier, T., Larsson, H.: Spatial filtering for detection of partly occluded targets. To be published in Optical Engineering, 50 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Christina Grönwall
    • 1
  • Gustav Tolt
    • 1
  1. 1.Division of Information SystemsFOI (Swedish Defence Research Agency)LinköpingSweden

Personalised recommendations