Abstract
Moving object detection is one of the significant tasks in computer vision. Robust Principal Component Analysis (RPCA) is a common method for moving object detection. However, this algorithm fails to effectively utilize the low-rank prior information of the background and the spatio-temporal continuity of the foreground, and exhibits degraded performance in the existence of shadows, photometric variations, rapidly moving objects, dynamic backgrounds, and jitters. Therefore, a new model via RPCA framework using non-convex low-rank approximation and total variational regularization is proposed to detect moving objects. Firstly, this paper introduces a non-convex function to deal with the problem that the nuclear norm excessively penalizes large singular values for the sake of constraining the low-rank characteristics of video background availably. Then, the sparsity is strengthened with the l1-norm and the spatio-temporal continuity of the foreground is explored by TV regularization. Finally, the augmented Lagrange multiplier algorithm is expanded by the alternating direction multiplier strategy to solve the model. Extensive experiments show that the proposed method outperforms existing methods in terms of the accuracy of moving object detection and foreground extraction effect.
Similar content being viewed by others
References
Bouwmans, T., Zahzah, E.H.: Robust PCA via principal component pursuit: a review for a comparative evaluation in video surveillance. Comput. Vis. Image Underst. 122(5), 22–34 (2014). https://doi.org/10.1016/j.cviu.2013.11.009
Bouwmans, T., Sobral, A., Javed, S., et al.: Decompositi on 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(2), 1–71 (2017). https://doi.org/10.1016/j.cosrev.2016.11.001
Kim, J.S., Dong, H.Y., Joo, Y.H.: Fast and robust algorithm of tracking multiple moving objects for intelligent video surveillance systems. IEEE Trans. Consum. Electron. 57(3), 1165–1170 (2011). https://doi.org/10.1109/TCE.2011.6018870
Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010). https://doi.org/10.1016/j.imavis.2009.11.014
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), 13–25 (2006). https://doi.org/10.1145/1177352.1177355
Aufrichtig, R., Wilson, D.L.: X-ray fluoroscopy spatio-temporal filtering with object detection. IEEE Trans. Med. Imaging 14(4), 733–746 (1995). https://doi.org/10.1109/42.476114
Shi, G., Tao, H., Dong, W., et al.: Robust foreground estimation via structured gaussian scale mixture modeling. IEEE Trans. Image Process. 27(10), 4810–4824 (2018). https://doi.org/10.1109/TIP.2018.2845123
Barnich, O., Droogenbroeck, M.V.: ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011). https://doi.org/10.1109/TIP.2010.2101613
Hofmann, M., Tiefenbacher, P., Rigoll, G.: Background segmentation with feedback: The pixel-based adaptive segmenter. In: IEEE Computer Society Conference on Computer Vision And Pattern Recognition Workshops (CVPR), pp. 38–43 (2012). doi:https://doi.org/10.1109/TIP.2010.2101613
Cande, E.J., Xiaodong, L., et al.: Robust principal component analysis? J. ACM 58(5), 289–298 (2009). https://doi.org/10.1145/1970392.1970395
Kang, Z., Peng, C., Cheng, Q.: Robust PCA via nonconvex rank approximation. In: IEEE International Conference on Data Mining (ICDM), pp. 211–220 (2015). doi: https://doi.org/10.1109/ICDM.2015.15
Hu, Z., Wang, Y., Su, R., et al.: Moving object detection based on non-convex RPCA with segmentation constraint. IEEE Access. 8(2), 41026–41036 (2020). https://doi.org/10.1109/ACCESS.2020.2977273
Yang, Z., Fan, L., Yang, Y., et al.: Generalized singular value thresholding operator based nonconvex low-rank and sparse decomposition for moving object detection. J. Franklin Inst. 356(16), 10138–10154 (2019). https://doi.org/10.1016/j.jfranklin.2019.09.017
Wen, F., Ying, R., Liu, P., et al.: Nonconvex regularized robust PCA using the proximal block coordinate descent algorithm. IEEE Trans. Signal Process. 67(20), 5402–5416 (2019). https://doi.org/10.1109/TSP.2019.2940121
Cao, X., Liang, Y., Guo, X.: Total variation regularized RPCA for irregularly moving object detection under dynamic background. IEEE Trans. Cybern. 46(4), 1014–1027 (2015). https://doi.org/10.1109/TCYB.2015.2419737
Shijila, B., Tom, A.J., George, S.N.: Moving object detection by low rank approximation and l1-TV regularization on RPCA framework. J. Vis. Commun. Image Represent. 56(10), 188–200 (2018). https://doi.org/10.1016/j.jvcir.2018.09.009
Zhou, X., Yang, C., Yu, W.: Moving object detection by detecting contiguous outliers in the low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 597–610 (2013). https://doi.org/10.1109/TPAMI.2012.132
Chen, C., Li, S., Qin, H., et al.: Robust salient motion detection in non-stationary videos via novel integrated strategies of spatio-temporal coherency clues and low-rank analysis. Pattern Recogn. 52, 410–432 (2016). https://doi.org/10.1016/j.patcog.2015.09.033
Ebadi, S.E., Ones, V.G., Izquierdo, E.: Efficient background subtraction with low-rank and sparse matrix decomposition. In: IEEE International Conference on Image Processing (ICIP), pp. 4863–4867 (2015). doi: https://doi.org/10.1109/ICIP.2015.7351731
Gao, C., Moore, B.E., Nadakuditi, R.R.: Augmented robust PCA for foreground-background separation on noisy, moving camera video. In: IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 1240–1244 (2017). doi: https://doi.org/10.1109/GlobalSIP.2017.8309159
Rodriguez, P., Chau, G.: Panning and jitter invariant incremental principal component pursuit for video background modeling. In: IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1844–1852 (2017). doi: https://doi.org/10.1109/ICCVW.2017.218
Lu, C., Feng, J., Chen, Y., et al.: Tensor robust principal component analysis with a new tensor nuclear norm. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 925–938 (2020). https://doi.org/10.1109/TPAMI.2019.2891760
Cai, S., Luo, Q., Yang, M., et al.: Tensor robust principal component analysis via non-convex low rank approximation. Appl. Sci. 9(7), 1411 (2019). https://doi.org/10.3390/app9071411
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D-Nonlinear Phenomena. 60(1–4), 259–268 (1992). https://doi.org/10.1016/0167-2789(92)90242-F
Madathil, B., George, S.N.: Twist tensor total variation regularized-reweighted nuclear norm based tensor completion for video missing area recovery. Inf. Sci. 423(1), 376–397 (2018). https://doi.org/10.1016/j.ins.2017.09.058
Phuc, N.T., Tao, P.D.: A continuous DC programming approach to the strategic supply chain design problem from qualified partner set. Eur. J. Oper. Res. 183(3), 1001–1012 (2007). https://doi.org/10.1016/j.ejor.2005.06.079
Beck, A., Teboulle, M.: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans. Image Process. 18(11), 2419–2434 (2009). https://doi.org/10.1109/TIP.2009.2028250
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant (Nos. 62173127, 61803146 and 61973104), the Scientific and Technological Innovation Leaders in Central Plains (No. 224200510008), the Henan Excellent Young Scientists Fund (No. 212300410036), the Program for Science and Technology Innovation Talents in Universities of Henan Province under Grant (No. 21HASTIT029), the Training Program for Young Backbone Teachers in Universities of Henan Province under Grant (No. 2019GGJS089), the Key Science and Technology Projects in Henan Province under Grant (Nos. 212102210169 and 212102210086), the Innovative Funds Plans of Henan University of Technology under Grant (No. 2020ZKCJ06), the Zhengzhou Science and Technology Collaborative Innovation Project (No. 21ZZXTCX06), the Cultivation Program of Young Backbone Teachers in Henan University of Technology under Grant chentianfei, the Open Fund from Research Platform of Grain Information Processing Center in Henan University of Technology under Grant (Nos. KFJJ-2020-107, KFJJ-2020-111 and KFJJ-2020-114).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, T., Zhao, D., Sun, L. et al. Moving object detection via RPCA framework using non-convex low-rank approximation and total variational regularization. SIViP 17, 109–117 (2023). https://doi.org/10.1007/s11760-022-02210-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-022-02210-6