Abstract
This paper presents a new Global Foreground Modeling (GFM) and Local Background Modeling (LBM) method for video analysis. First, a novel feature vector, which integrates the RGB values, the horizontal and vertical Haar wavelet features, and the temporal difference features of a pixel, enhances the discriminatory power due to its increased dimensionality. Second, the local background modeling process chooses the most significant single Gaussian density to model the background locally for each pixel according to the weights learned for the Gaussian mixture model. Third, an innovative global foreground modeling method, which applies the Bayes decision rule, models the foreground pixels globally. The GFM method thus is able to achieve improved foreground detection accuracy and capable of detecting stopped moving objects. Experimental results using the New Jersey Department of Transportation (NJDOT) traffic video sequences show that the proposed method achieves better video analysis results than the popular background subtraction methods.
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
Similar content being viewed by others
References
Bouwmans, T., Sobral, A., Javed, S., Jung, S.K., Zahzah, E.: Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset. Comput. Sci. Rev. 23, 1–71 (2017)
Sobral, A., Vacavant, A.: A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput. Vis. Image Underst. 122, 4–21 (2014)
Bouwmans, T., Silva, C., Marghes, C., Zitouni, M.S., Bhaskar, H., Frélicot, C.: On the role and the importance of features for background modeling and foreground detection. CoRR abs/1611.09099 (2016)
Barnich, O., Droogenbroeck, M.V.: ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011)
Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, UK, 23–26 August 2004, pp. 28–31. IEEE Computer Society (2004)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: 1999 Conference on Computer Vision and Pattern Recognition (CVPR 1999), 23–25 June 1999, Ft. Collins, CO, USA, pp. 2246–2252. IEEE Computer Society (1999)
Hayman, E., Eklundh, J.: Statistical background subtraction for a mobile observer. In: 9th IEEE International Conference on Computer Vision (ICCV 2003), 14–17 October 2003, Nice, France, pp. 67–74. IEEE Computer Society (2003)
Liu, C. (ed.): Recent Advances in Intelligent Image Search and Video Retrieval. Springer, Heidelberg (2017). https://doi.org/10.1007/978-3-319-52081-0
Liu, Q., Liu, C.: A novel locally linear KNN method with applications to visual recognition. IEEE Trans. Neural Netw. Learn. Syst. 28(9), 2010–2021 (2017)
Puthenputhussery, A., Liu, Q., Liu, C.: A sparse representation model using the complete marginal fisher analysis framework and its applications to visual recognition. IEEE Trans. Multimed. 19(8), 1757–1770 (2017)
Chen, S., Liu, C.: Eye detection using discriminatory haar features and a new efficient SVM. Image Vis. Comput. 33, 68–77 (2015)
Chen, S., Liu, C.: Clustering-based discriminant analysis for eye detection. IEEE Trans. Image Process. 23(4), 1629–1638 (2014)
Varadarajan, S., Miller, P.C., Zhou, H.: Region-based mixture of gaussians modelling for foreground detection in dynamic scenes. Pattern Recogn. 48(11), 3488–3503 (2015)
Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based models. In: Metaxas, D.N., Quan, L., Sanfeliu, A., Gool, L.J.V. (eds.): IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6–13, 2011, pp. 1307–1314. IEEE Computer Society (2011)
Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.: Pfinder: real-time tracking of the human body. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 780–785 (1997)
Liu, C.: A Bayesian discriminating features method for face detection. IEEE Trans. Pattern Anal. Mach. Intell. 25(6), 725–740 (2003)
Mittal, A., Huttenlocher, D.P.: Scene modeling for wide area surveillance and image synthesis. In: 2000 Conference on Computer Vision and Pattern Recognition (CVPR 2000), 13–15 June 2000, Hilton Head, SC, USA, pp. 2160–2167. IEEE Computer Society (2000)
Grove, T., Baker, K.D., Tan, T.N.: Colour based object tracking. In: Jain, A.K., Venkatesh, S., Lovell, B.C. (eds.) Fourteenth International Conference on Pattern Recognition, ICPR 1998, Brisbane, Australia, 16–20 August, 1998, pp. 1442–1444. IEEE Computer Society (1998)
Webb, A.R.: Statistical Pattern Recognition. Wiley, Hoboken (2003)
Acknowledgments
This paper is partially supported by the NSF grant 1647170.
Author information
Authors and Affiliations
Corresponding authors
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
Shi, H., Liu, C. (2018). A New Global Foreground Modeling and Local Background Modeling Method for Video Analysis. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2018. Lecture Notes in Computer Science(), vol 10934. Springer, Cham. https://doi.org/10.1007/978-3-319-96136-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-96136-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96135-4
Online ISBN: 978-3-319-96136-1
eBook Packages: Computer ScienceComputer Science (R0)