Skip to main content
SpringerLink
Log in

An improved Gaussian mixture modeling algorithm combining foreground matching and short-term stability measure for motion detection

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Although deep learning has been successfully applied in image analysis, the conventional Gaussian Mixture Modeling (GMM) method still has great potential for multi-mode motion detection because it does not require the support of specialized hardware such as GPUs and massive training data. Under the framework of GMM, this paper combines foreground matching and short-term stability measure to detect slow-moving objects. Foreground models built and updated using the detected foreground pixels have the priority to match potential foreground in the incoming pixels. Meanwhile, the pixel-level stability is measured to make sure that an integrated foreground is detected when a dynamic foreground process is followed. The combination of foreground matching and short-term stability measure greatly improves GMM’s tolerance to slow-moving objects. The quantitative evaluation demonstrates the effectiveness of the proposed algorithm to robustly detect slow-moving objects under a variety of real environments with distracting motions such as illumination changes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Agaian SS, Yeole RD, Reinecke G et al (2016) Comparison study of Gaussian mixture models for fingerprint image duplication with a new model. Electronic Imaging 15:1–7

  2. Bommes M, Fazekas A, Volkenhoff T et al (2016) Video based intelligent transportation systems–state of the art and future development. Transport Res Proced 14:4495–4504

  3. Boulmerka A, Allili MS (2017) Foreground segmentation in videos combining general Gaussian mixture modeling and spatial information. IEEE Trans on Circuit and Syst for Video Technol 28(6):1330–1345

    Article  Google Scholar 

  4. Cao X, Yang L, Guo X (2015) Total variation regularized RPCA for irregularly moving object detection under dynamic background. IEEE Trans on Cybernetics 46(4):1014–1027

    Article  Google Scholar 

  5. Cao Y, Shen C, Shen HT (2017) Exploiting depth from single monocular images for object detection and semantic segmentation. IEEE Trans Image Process 26(2):836–846

    Article  MathSciNet  Google Scholar 

  6. Chang X, Ma Z, Lin M et al (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans on Image Process 26(8):3911–3920

    Article  MathSciNet  Google Scholar 

  7. Chen C, Shuai L, Hong Q et al (2016) 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

    Article  Google Scholar 

  8. Cheng KW, Chen YT, Fang WH (2015) Gaussian process regression-based video anomaly detection and localization with hierarchical feature representation. IEEE Trans on Image Process 24(12):5288–5301

    Article  MathSciNet  Google Scholar 

  9. Collins RT, Lipton AJ, Kanade T et al (2000) A system for video surveillance and monitoring. VSAM final report 2000:1-68

  10. Diego O, Sanmiguel JC, Martinez JM (2018) Hierarchical improvement of foreground segmentation masks in background subtraction. IEEE Trans on Circuits and Syst for Video Technol 29(6):1645–1658

    Google Scholar 

  11. Haag M, Nagel HH (2000) Incremental recognition of traffic situations from video image sequences. Image Vis Comput 18(2):137–153

    Article  Google Scholar 

  12. Haritaoglu I, Hanrwood D, Davis L (2010) Real-time surveillance of people and their activilies. IEEE Trans on Pattern Anal and Mach Intell 22(8):809–830

    Article  Google Scholar 

  13. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. IEEE conference on computer vision and pattern recognition (CVPR). IEEE Comput Soc 2016:770–778

    Google Scholar 

  14. Kaiming H, Georgia G, Piotr D et al (2017) Mask R-CNN. IEEE Trans on Pattern Anal and Mach Intell 99:1–12

    Google Scholar 

  15. Krizhevsky A, Sutskever I, Hinton G E (2012) ImageNet classification with deep convolutional neural networks. Adv in Neural Inform Process Syst 2012:1097-1105

  16. Kumar PMA, Vaidehi V, Chandralekha E (2013) Video traffic analysis for abnormal event detection using frequent item set mining. IEEE Int Conf on Recent Trends in Inform Technol 2013:551–556

    Google Scholar 

  17. Kumaran N, Vadivel A, Kumar S et al (2018) Recognition of human actions using CNN-GWO: a novel modeling of CNN for enhancement of classification performance. Multimed Tools Appl 1:1–33

    Google Scholar 

  18. Lin G, Milan A, Shen C et al (2017) RefineNet: multi-path refinement networks for high-resolution semantic segmentation. IEEE Conf on Comput Vis and Pattern Recogn (CVPR) 2017:1925–1934

    Google Scholar 

  19. Liu W, Yu H, Yuan H et al (2014) Effective background modelling and subtraction approach for moving object detection. IET Comput Vis 9(1):13–24

    Article  Google Scholar 

  20. Liu Z, Li J, Shen Z, et al (2015) Learning efficient convolutional networks through network slimming. Proceedings of the IEEE international conf on comput vis (ICCV) 2017:2736-2744

  21. Min W, Yubao S, Renlong H et al (2018) Multi-component group sparse RPCA model for motion object detection under complex dynamic background. Neurocomputing 314:120–131

    Article  Google Scholar 

  22. Niranjil KA, Sureshkumar C (2015) Background subtraction in dynamic environment based on modified adaptive GMM with TTD for moving object detection. Journal of Electr Engineering & Technol 10(1):372–378

    Article  Google Scholar 

  23. Onofri L, Soda P, Pechenizkiy M et al (2016) A survey on using domain and contextual knowledge for human activity recognition in video streams. Expert Syst Appl 63:97–111

    Article  Google Scholar 

  24. Parekh HS, Thakore DG, Jaliya UK (2014) A survey on object detection and tracking methods. International Journal of Innovative Research in Comput and Commun Eng 2(2):2970–2979

    Google Scholar 

  25. Park JW, Song BC (2016) Night-time vehicle detection using low exposure video enhancement and lamp detection. IEEE Int Conf Electron inform, and Commun (ICEIC) 2016:1–2

    Google Scholar 

  26. Puhan S, Rout DK, Kamila NK (2013) Slow and fast moving object detection under illumination variation condition. Am J Signal Process 3(5):121–131

  27. Rasouli A, Kotseruba I, Tsotsos JK (2018) Understanding pedestrian behavior in complex traffic scenes. IEEE Trans on Intell Veh 3(1):61–70

  28. Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. IEEE Conf on comput vis and pattern recogn (CVPR) 2014:806-813

  29. Redmon J, Divvala S, Girshick R, et al (2016) You only look once: unified, real-time object detection. IEEE Conf on Comput Vis and Pattern Recogn (CVPR) 2016:779-788

  30. Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal & Mach Intell 39(6):1137–1149

    Article  Google Scholar 

  31. Sahoo PK, Kanungo P, Mishra S (2018) A fast valley-based segmentation absurb for detection of slowly moving objects. Signal, Image and Video Process 12(7):1265–1272

    Article  Google Scholar 

  32. Sehairi K, Chouireb F, Meunier J (2017) Comparative study of motion detection methods for video surveillance systems. Journal of Electr Imaging 26(2):023025

    Article  Google Scholar 

  33. Shafiee MJ, Chywl B, Li F, Wong A (2017) Fast YOLO: a fast you only look once system for real-time embedded object detection in video. arXiv preprint 2017:05943

  34. Shafiee MJ, Siva P, Fieguth P et al (2018) Real-time embedded motion detection via neural response mixture modeling. Journal of Signal Process Syst 90(6):931–946

    Article  Google Scholar 

  35. Sivaraman S, Trivedi MM (2013) Looking at vehicles on the road: a survey of vision-based vehicle detection, tracking, and behavior analysis. IEEE Trans on Intelligent Transportation Systems 14(4):1773–1795

    Article  Google Scholar 

  36. Song Y, Noh SJ, Yu J et al (2014) Background subtraction based on Gaussian mixture models using color and depth information. Control, Automat and Inform Sci (ICCAIS) 2014:132–135

    Google Scholar 

  37. Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. IEEE, CVPR 2:246–252

    Google Scholar 

  38. Subudhi B N, Nanda P K (2009) Detection of slow moving video objects using compound Markov random Field model. TENCON 2008 - 2008 IEEE Region 10 Conf 2008:1-6

  39. Tsai CL, Tai SC (2013) Traffic monitoring and event analysis at intersection based on integrated multi-video and petri net process. J Mar Sci Technol 21(6):639–646

    Google Scholar 

  40. Utasi A, Czúni L (2007) Reducing the foreground aperture problem in mixture of Gaussians based motion detection. In: IWSSIP 2007/EP-SIPMCS 2007 2007:157-160

  41. Vishwakarma S, Agrawal A (2013) A survey on activity recognition and behavior understanding in video surveillance. Vis Comput 29(10):983–1009

    Article  Google Scholar 

  42. Wang H, Suter D (2005) A re-evaluation of mixture of Gaussian background modeling. In: ICASSP, Int. Conf. On. IEEE 2:1017-1020

  43. Wang Y, Luo Z, Jodoin PM (2017) Interactive deep learning method for segmenting moving objects. Pattern Recogn Lett 96:66–75

    Article  Google Scholar 

  44. Xin B, Tian Y, Wang Y et al (2015) Background subtraction via generalized fused lasso foreground modeling. Proc of the IEEE Conf on CVPR 2015:4676–4684

    Google Scholar 

  45. Xu Y, Dong J, Zhang B et al (2016) Background modeling methods in video analysis: a review and comparative evaluation. CAAI Trans on Intell Technol 1(1):43–60

    Article  Google Scholar 

  46. Yan J, Xu Q, Duan H et al (2017) Slow ground moving object detection in rotating complex background. Journal of Imaging Sci & Technol 61(2):20507-1–20507-16

    Article  Google Scholar 

  47. Yang T, Wang X, Yao B et al (2016) Small moving vehicle detection in a satellite video of an urban area. Sensors 16(9):1528

    Article  Google Scholar 

  48. Zhang G, Zhang D, Li D et al (2016) Research on key Technologies of Video Intelligent Identification and Security Management and control system in substation. Int Journal of Simulation--Systems, Sci & Technol 17(20):6.1–6.6

    Google Scholar 

Download references

Acknowledgements

The research work described in this paper is supported by the Natural Science Foundation of Anhui Province (1908085MF203), Anhui Provincial Natural Science Research Project of Colleges and Universities (No. KJ2017A012), the open project of Key lab of Optic-electronic Information Acquisition and Manipulation Ministry of Education, Anhui University (OEIAM201401), and the Ph.D research startup foundation of Anhui University. The authors would like to thank all members of the Intelligent Video Research Group from the IIP-HCI lab of Anhui University for their valuable suggestions and assistance in preparing this paper.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Anhui University, Hefei, 230601, China

    Chao Zhang, Xiaopei Wu & Xiangping Gao

Authors
  1. Chao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaopei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiangping Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaopei Wu.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, C., Wu, X. & Gao, X. An improved Gaussian mixture modeling algorithm combining foreground matching and short-term stability measure for motion detection. Multimed Tools Appl 79, 7049–7071 (2020). https://doi.org/10.1007/s11042-019-08210-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-08210-y

Keywords

Search

Navigation