Abstract
Kernel density estimation algorithm is an effective method to segment fore/background, but the computation of kernel density estimation is complexity. The conditions of dynamic scene of backgrounds and light mutational change make the robustness of the method is not good enough. Correlation coefficient is an effective method to describe the similarity of images, and the method is not sensitive when the image changes and has small differences in the intensity. A hierarchical block detection mechanism is proposed. First of all, the disturbance of the dynamic background scene and the light mutation are filtered by the correlation coefficient. And then, the block with fore-ground is segmented by kernel density estimation. Experiments confirmed that the proposed method is effective under the dynamic background disturbance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Mittaland, A., Huttenlocher, D.: Scene modeling for wide area surveillance and image synthesis. In: IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 160–167 (2000)
Huang, S.S., Fu, L.C., Hsiao, P.Y.: Region-level motion-based background modeling and subtraction using MRFs. IEEE Transactions on Image Processing 16(5), 1446–1456 (2007)
Koller, D., Weber, J., Huang, T., et al.: Towards robust automatic traffic scene analysis in real-time. In: Proceedings of International Conference on Pattern Recognition, Jerusalem, Palestine, pp. 1262–1311 (1994)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, USA, pp. 2462–2521 (1999)
Stauffer, C., Grimson, W.E.L.: Learning patterns of activity using real-time tracking. IEEE Trans. PAMI 22(8), 474–757 (2000)
Elgammal, A., Duraiswami, R., Harwood, D., et al.: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of IEEE 90(7), 1151–1163 (2002)
Yan-fen, M.A.O., Peng-fei, S.H.I.: Kernel Density Estimation for Dynamic Scene Modeling. Journal of Data Acquisition & Processing 19(4), 391–394 (2004)
Chen, G., Zhou, H.-Q., Yan, J.-F.: Real-time Back-ground Subtraction and Moving Shadow Detection Based on UKF Modeling. Journal of Image and Graphics 14(5), 931–937 (2009)
Wei, C.-A., Jiang, S.-D., Sun, C.: Small Target Tracking in Forward Looking Infrared Iimagery Based on Kernel Density Estimation. Journal of Harbin Engineering University 30, 763–767 (2009)
Gu, J.-D., Liu, Z., Zhang, Z.-Y.: A Novel Moving Object Segmenta-tion Algorithm Using Kernel Density Estimation and Edge Information. Journal of Computer-Aided Design & Computer Graphics 21(2), 223–228 (2009)
Zhu, Y.-S., Guo, C.-M.: Research of Correlation Tracking Algorithm Based on Correlation Coefficient. Journal of Image and Graphics 9(8), 963–967 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Rui, T., Yang, Z., Zhou, Y., Fang, H., Zhu, J. (2013). Target Detection Based on Kernel Density Estimation Combined with Correlation Coefficient. In: Huet, B., Ngo, CW., Tang, J., Zhou, ZH., Hauptmann, A.G., Yan, S. (eds) Advances in Multimedia Information Processing – PCM 2013. PCM 2013. Lecture Notes in Computer Science, vol 8294. Springer, Cham. https://doi.org/10.1007/978-3-319-03731-8_72
Download citation
DOI: https://doi.org/10.1007/978-3-319-03731-8_72
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03730-1
Online ISBN: 978-3-319-03731-8
eBook Packages: Computer ScienceComputer Science (R0)