Abstract
In this paper two new schemes are proposed for fusion of the results from video decomposition by Robust Principal Component Analysis and Non-negative Matrix Factorization with the aim of detecting moving objects over stationary background. The schemes use the logical OR and AND operators on a pixel basis over the binary outputs of the base decomposition algorithms. Experimental results from testing with videos, containing natural scenes with humans and vehicles, reveal the applicability of both schemes with higher Detection Rate for the OR operator and considerably higher Precision for the AND operator. The latter gets the highest F-measure of 0.8168 and is considered applicable in various systems where higher reliability is sought. Execution times for all tested implementations are practical, although allowing further optimization, which renders the proposed algorithms applicable in a wide set of applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Javed, S., Mahmood, A., Al-Maadeed, S., Bouwmans, T., Jung, S.K.: Moving object detection in complex scene using spatiotemporal structured-sparse RPCA. IEEE Trans. Image Process. 28(2), 1007–1022 (2018)
Cao, X., Yang, L., Guo, X.: Total variation regularized RPCA for irregularly moving object detection under dynamic background. IEEE Trans. Cybern. 46(4), 1014–1027 (2015)
Javed, S., Mahmood, A., Bouwmans, T., Soon, K.J.: Superpixels based manifold structured sparse RPCA for moving object detection. In: International Workshop on Activity Monitoring by Multiple Distributed Sensing, BMVC 2017, Londres, United Kingdom, September (2017)
Li, Y., Liu, G., Liu, Q., Sun, Y., Chen, S.: Moving object detection via segmentation and saliency constrained RPCA. Neurocomputing 323, 352–362 (2019)
Javed, S., Bouwmans, T., Sultana, M., Jung, S.K.: Moving object detection on RGB-D videos using graph regularized spatiotemporal RPCA. In: International Conference on Image Analysis and Processing, pp. 230–241, Springer, Cham (2017)
Chen, B.H., Shi, L.F., Ke, X.: A robust moving object detection in multi-scenario big data for video surveillance. IEEE Trans. Circuits Syst. Video Technol. 29(4), 982–995 (2018)
Fan, X.N., Xue, R.Y., Shi, P.F., Li, M., Ni, J.J.: Moving object detection based on NMF and similarity analysis. Comput. Mod. 04 (2018)
Rezaei, B., Ostadabbas, S.: Moving object detection through robust matrix completion augmented with objectness. IEEE J. Sel. Top. Signal Process. 12(6), 1313–1323 (2018)
Yang, X., Liu, D., Zhou, D., Yang, R.: Moving cast shadow detection using block nonnegative matrix factorization. Bull. Pol. Acad. Sci. Tech. Sci. 66(2), 229–235 (2018)
Zhou, T., Tao, D.: Godec: randomized low-rank & sparse matrix decomposition in noisy case. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011, June 28–July 2, Bellevue, WA, USA, pp. 33–40. ACM, New York, USA (2011)
Aravkin, A., Becker, S., Cevher, V., Olsen, P.: A variational approach to stable principal component pursuit. In: Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence, July 23–27, Quebec City, Quebec, Canada, pp. 32–41. AUAI Press, Corvallis, Oregon, USA (2014)
Guan, N., Tao, D., Luo, Z., Shawe-Taylor, J.: MahNMF: Manhattan non-negative matrix factorization. arXiv preprint arXiv:1207.3438 (2012)
Bucak, S., Gunsel, B., Gursoy, O.: Incremental nonnegative matrix factorization for background modeling in surveillance video. In: 2007 IEEE 15th Signal Processing and Communications Applications, pp. 1–4. IEEE (2007)
Sobral, A., Bouwmans, T., Zahzah, E.H.: Lrslibrary: Low-rank and sparse tools for background modeling and subtraction in videos. Robust Low-Rank and Sparse Matrix Decomposition: Applications in Image and Video Processing. CRC Press, Boca Raton, FL, USA (2016)
Cuevas, C., Yáñez, E.M., García, N.: Labeled dataset for integral evaluation of moving object detection algorithms: LASIESTA. Comput. Vis. Image Underst. 152, 103–117 (2016)
Guyon, C., Bouwmans, T., Zahzah, E.H.: Robust principal component analysis for background subtraction: Systematic evaluation and comparative analysis. Princ. Compon. Anal. 10, 223–238 (2012)
Acknowledgements
This work was supported by the National Science Fund of Bulgaria: KP-06-H27/16 “Development of efficient methods and algorithms for tensor-based processing and analysis of multidimensional images with application in interdisciplinary areas”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Draganov, I., Mironov, R. (2022). Object Motion Detection in Video by Fusion of RPCA and NMF Decompositions. In: Kountchev, R., Mironov, R., Nakamatsu, K. (eds) New Approaches for Multidimensional Signal Processing. Smart Innovation, Systems and Technologies, vol 270. Springer, Singapore. https://doi.org/10.1007/978-981-16-8558-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-16-8558-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8557-6
Online ISBN: 978-981-16-8558-3
eBook Packages: EngineeringEngineering (R0)