Abstract
Classical Gaussian mixture model (GMM) can represent the multi-states of a single pixel. GMM is robust when dealing with complex scenes with gradual-changed illumination. However, it still leads to false detection because of the change of pixel values in the same position when the background scenes get revealed after being covered. In this paper, a Context-Awareness based Gaussian mixture model (CAGMM) is proposed to tag the Gaussian model which used to be background. Experimental results show that the proposed CAGMM can remember scenes and adapt to the change of scenes more quickly, thus the false detection rate is reduced.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gamboa-Aispuro, J.M., Aguilar-Ponce, R.M., Tecpanecatl-Xihuitl, J.L.: Background subtraction based on mutual information. In: IEEE International Autumn Meeting on Power, Electronics and Computing. Institute of Electrical and Electronics Engineers Inc., Mexico (2016)
Ge, W., et al.: Dynamic background estimation and complementary learning for pixel-wise foreground/background segmentation. Pattern Recogn. 59, 112–125 (2016)
Dong, Y., Desouza, G.N.: Adaptive learning of multi-subspace for foreground detection under illumination changes. Comput. Vis. Image Underst. 115, 31–49 (2011)
Stauffer C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO (1999)
Wang, K., Liang, Y., Xing, X., Zhang, R.: Target detection algorithm based on gaussian mixture background subtraction model. In: Deng, Z., Li, H. (eds.) Proceedings of the 2015 Chinese Intelligent Automation Conference. LNEE, vol. 336, pp. 439–447. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-46469-4_47
Kim, W., Kim, C.: Background subtraction for dynamic texture scenes using fuzzy color histograms. IEEE Sig. Process. Lett. 19(3), 127–130 (2012)
Wang, Z., Zhang, L., Bao, H.: Adaptive background model based on hybrid structure neural network. Acta Electronica Sinica 39(5), 1053–1058 (2011)
Han, B., Davis, L.S.: Density-based multifeature background subtraction with support vector machine. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 1017–1023 (2012)
Lin, H.-H., Chuang, J.-H., Liu, T.-L.: Regularized background adaptation: a novel learning rate control scheme for gaussian mixture modeling. IEEE Trans. Image Process. 20(3), 822–836 (2011)
Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: IEEE International Conference on Pattern Recognition, pp. 28–31. IEEE (2004)
Cheng, F.-C., Huang, S.-C., Ruan, S.-J.: Illumination-sensitive background modeling approach for accurate moving object detection. IEEE Trans. Broadcast. 57(4), 794–801 (2011)
Zuo, J., Liang, Y., Zhao, C., et al.: Gaussian mixture background model based on entropy image and membership-degree-image. J. Electron. Inf. Technol. 30(8), 1918–1922 (2008)
Qi, Y.-J., Wang, Y.-J., Li, Y.-P.: Memory-based Gaussian mixture background modeling. Acta Automatica Sinica 36(11), 1520–1526 (2010)
Xiao, J., et al.: Hierarchical tone mapping based on image colour appearance model. IET Comput. Vis. 8(4), 358–364 (2014)
Wang, Y., Jodoin, P.-M., Porikli, F., et al.: CDnet 2014: an expanded change detection benchmark dataset. In: Proceedings of the IEEE Workshop on Change Detection (CDW-2014) at CVPR-2014, pp. 387–394 (2014)
Acknowledgment
This paper was partially funded by the Natural Science Foundation of Hubei Province (Grant No. 2014CFB585), and the Natural Science Foundation of China (Grant No. 61573002).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Xie, H., Xiao, J., Lei, J. (2018). Context-Awareness Based Adaptive Gaussian Mixture Background Modeling. In: Satoh, S. (eds) Image and Video Technology. PSIVT 2017. Lecture Notes in Computer Science(), vol 10799. Springer, Cham. https://doi.org/10.1007/978-3-319-92753-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-92753-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92752-7
Online ISBN: 978-3-319-92753-4
eBook Packages: Computer ScienceComputer Science (R0)