A new spatio-temporal background–foreground bimodal for motion segmentation and detection in urban traffic scenes


Automatic vehicle detection in urban traffic surveillance is an important and urgent issue, since it provides necessary information for further processing. Conventional techniques utilize either motion segmentation or appearance-based detection, which involves either poor adaptation or high computation. The complexity of urban traffic scenarios lies in slow motion temporarily stopped or parked vehicles, dynamic background, and sudden illumination variations. In this paper, a new motion segmentation technique is proposed based on spatio-temporal background–foreground bimodal. The temporal background information is modeled using a weighted sigma–delta estimation, cumulative frame differencing is used to model the foreground pixels, and the spatial correlation between neighboring pixels is utilized to combine both background and foreground models. The median of consecutive frame difference adapts sudden illumination variation, update background model, and reinitialize foreground model. Comparative experimental results for typical urban traffic sequences show that the proposed technique achieves robust and accurate segmentation, which improves adaptation, reduce false detection, and satisfy real-time requirements.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  1. 1.

    Abdulrahim K, Salam RA (2016) Traffic surveillance: a review of vision based vehicle detection, recognition and tracking. Int J Appl Eng Res 11:713–726

    Google Scholar 

  2. 2.

    Al-Nawashi Malek, Al-Hazaimeh Obaida M, Saraee Mohamad (2017) A novel framework for intelligent surveillance system based on abnormal human activity detection in academic environments. Neural Comput Appl 28:565–572

    Article  Google Scholar 

  3. 3.

    Vargas M, Milla JM, Toral SL, Barrero F (2010) An enhanced background estimation algorithm for vehicle detection in urban traffic scenes. IEEE Trans Veh Technol 59:3694–3709

    Article  Google Scholar 

  4. 4.

    Cuevas Rodríguez C, Martínez Sanz R, Berjón Díez D, García Santos N (2017) Detection of stationary foreground objects using multiple nonparametric background-foreground models on a finite state machine. IEEE Trans Image Process 26:1127–1142

    MathSciNet  Article  Google Scholar 

  5. 5.

    Chuntian C, Chau K-W (2002) Three-person multi-objective conflict decision in reservoir flood control. Eur J Oper Res 142:625–631

    Article  Google Scholar 

  6. 6.

    Wu C, Chau K (2011) Rainfall–runoff modeling using artificial neural network coupled with singular spectrum analysis. J Hydrol 399:394–409

    Article  Google Scholar 

  7. 7.

    Buch N, Velastin SA, Orwell J (2011) A review of computer vision techniques for the analysis of urban traffic. IEEE Trans Intell Transp Syst 12:920–939

    Article  Google Scholar 

  8. 8.

    Li Q-L, He J-F (2011) Vehicles detection based on three-frame-difference method and cross-entropy threshold method. Comput Eng 37:172–174

    Google Scholar 

  9. 9.

    Chen M, Wei X, Yang Q, Li Q, Wang G, Yang M-H (2018) Spatiotemporal GMM for background subtraction with superpixel hierarchy. IEEE Trans Pattern Anal Mach Intell 40:1518–1525

    Article  Google Scholar 

  10. 10.

    Piccardi M (2004) Background subtraction techniques: a review. In: 2004 IEEE international conference on systems, man and cybernetics, pp 3099–3104

  11. 11.

    Liu Y, Lu Y, Shi Q, Ding J (2013) Optical flow based urban road vehicle tracking. In: 2013 ninth international conference on computational intelligence and security, pp 391–395

  12. 12.

    Romero JD, Lado MJ, Méndez AJ (2018) A background modeling and foreground detection algorithm using scaling coefficients defined with a color model called lightness-red-green-blue. IEEE Trans Image Process 27:1243–1258

    MathSciNet  Article  Google Scholar 

  13. 13.

    Manikandan R, Ramakrishnan R (2013) Video object extraction by using background subtraction techniques for sports applications. Digit Image Process 5:435–440

    Google Scholar 

  14. 14.

    Yaseen ZM, Sulaiman SO, Deo RC, Chau K-W (2019) An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387–408

    Article  Google Scholar 

  15. 15.

    Chen L-C, Hsieh J-W, Chiang H-F, Tsai T-H (2015) Real-time vehicle color identification using symmetrical SURFs and chromatic strength. In: 2015 IEEE international symposium on circuits and systems (ISCAS), pp 2804–2807

  16. 16.

    Sivaraman S, Trivedi MM (2013) Vehicle detection by independent parts for urban driver assistance. IEEE Trans Intell Transp Syst 14:1597–1608

    Article  Google Scholar 

  17. 17.

    Leotta MJ, Mundy JL (2010) Vehicle surveillance with a generic, adaptive, 3d vehicle model. IEEE Trans Pattern Anal Mach Intell 33:1457–1469

    Article  Google Scholar 

  18. 18.

    Zhong Z, Zhang B, Lu G, Zhao Y, Xu Y (2017) An adaptive background modeling method for foreground segmentation. IEEE Trans Intell Transp Syst 18:1109–1121

    Article  Google Scholar 

  19. 19.

    Wren CR, Azarbayejani A, Darrell T, Pentland AP (1997) Pfinder: Real-time tracking of the human body. IEEE Trans Pattern Anal Mach Intell 19:780–785

    Article  Google Scholar 

  20. 20.

    Al-Hazaimeh OM, Al-Nawashi M, Saraee M (2018) Geometrical-based approach for robust human image detection. Multimed Tools Appl 78:1–25

    Google Scholar 

  21. 21.

    McFarlane NJ, Schofield CP (1995) Segmentation and tracking of piglets in images. Mach Vis Appl 8:187–193

    Article  Google Scholar 

  22. 22.

    Manzanera A, Richefeu J (2004) A robust and computationally efficient motion detection algorithm based on sigma-delta background estimation. In: Indian conference on computer vision, graphics and image processing (ICVGIP’04)

  23. 23.

    Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: cvpr, p 2246

  24. 24.

    Barcellos P, Bouvié C, Escouto FL, Scharcanski J (2015) A novel video based system for detecting and counting vehicles at user-defined virtual loops. Expert Syst Appl 42:1845–1856

    Article  Google Scholar 

  25. 25.

    Choudhury SK, Sa PK, Bakshi S, Majhi B (2016) An evaluation of background subtraction for object detection vis-a-vis mitigating challenging scenarios. IEEE Access 4:6133–6150

    Article  Google Scholar 

  26. 26.

    Akilan T, Jonathan Wu QM, Yang Y (2018) Fusion-based foreground enhancement for background subtraction using multivariate multi-model Gaussian distribution. Inf Sci 430–431:414–431

    Article  Google Scholar 

  27. 27.

    Kim W, Jung C (2017) Illumination-invariant background subtraction: comparative review, models, and prospects. IEEE Access 5:8369–8384

    Article  Google Scholar 

  28. 28.

    Elgammal A, Harwood D, Davis L (2000) Non-parametric model for background subtraction. In: European conference on computer vision, pp 751–767

  29. 29.

    Kim K, Chalidabhongse TH, Harwood D, Davis L (2005) Real-time foreground–background segmentation using codebook model. Real-Time Imaging 11:172–185

    Article  Google Scholar 

  30. 30.

    Toyama K, Krumm J, Brumitt B, Meyers B (1999) Wallflower: principles and practice of background maintenance. In: The proceedings of the seventh IEEE international conference on computer vision, pp 255–261

  31. 31.

    Oliver NM, Rosario B, Pentland AP (2000) A Bayesian computer vision system for modeling human interactions. IEEE Trans Pattern Anal Mach Intell 22:831–843

    Article  Google Scholar 

  32. 32.

    Manzanera A, Richefeu JC (2007) A new motion detection algorithm based on Σ-Δ background estimation. Pattern Recogni Lett 28:320–328

    Article  Google Scholar 

  33. 33.

    Manzanera A (2007) σ-δ background subtraction and the Zipf law. In: Iberoamerican congress on pattern recognition, 2007, pp 42–51

  34. 34.

    Abutaleb M, Hamdy A, Abuelwafa M, Saad E (2009) FPGA-based object-extraction based on multimodal Σ-Δ background estimation. In: 2nd international conference on computer, control and communication, 2009. IC4 2009, pp 1–7

  35. 35.

    Toral S, Vargas M, Barrero F, Ortega M (2009) Improved sigma-delta background estimation for vehicle detection. Electron Lett 45:32–34

    Article  Google Scholar 

  36. 36.

    Lacassagne L, Manzanera A, Dupret A (2009) Motion detection: fast and robust algorithms for embedded systems. In: 2009 16th IEEE international conference on image processing (ICIP), pp 3265–3268

  37. 37.

    Li K, Yang Y (2011) A method for background modeling and moving object detection in video surveillance. In: 2011 4th international congress on image and signal processing (CISP), pp 381–385

  38. 38.

    Fang W, Zhang T, Zhao C, Soomro DB, Taj R, Hu H (2018) Background subtraction based on random superpixels under multiple scales for video analytics. IEEE Access 6:33376–33386

    Article  Google Scholar 

  39. 39.

    Moazenzadeh R, Mohammadi B, Shamshirband S, Chau K-W (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Eng Appl Comput Fluid Mech 12:584–597

    Google Scholar 

  40. 40.

    Gao T, Liu Z-g, Gao W-c, Zhang J (2008) Moving vehicle tracking based on SIFT active particle choosing. In: International conference on neural information processing, pp 695–702

  41. 41.

    Najafi B, Faizollahzadeh Ardabili S, Shamshirband S, Chau K-w, Rabczuk T (2018) Application of ANNs, ANFIS and RSM to estimating and optimizing the parameters that affect the yield and cost of biodiesel production. Eng Appl Computat Fluid Mech 12:611–624

    Google Scholar 

  42. 42.

    Fotovatikhah F, Herrera M, Shamshirband S, Chau K-W, Faizollahzadeh-Ardabili S, Piran MJ (2018) Survey of computational intelligence as basis to big flood management: Challenges, research directions and future work. Eng Appl Comput Fluid Mech 12:411–437

    Google Scholar 

  43. 43.

    Abdulrahim K, Salam RA (2016) Cumulative frame differencing for urban vehicle detection. In: First international workshop on pattern recognition, p 100110G

  44. 44.

    Li X, Ng MK, Yuan X (2015) Median filtering-based methods for static background extraction from surveillance video. Numer Linear Algebra Appl 22:845–865

    MathSciNet  Article  Google Scholar 

  45. 45.

    Ma’moun A, Al-hazaimeh OM, Alhindawi N, Hayajneh SM (2014) A dual curvature shell phased array simulation for delivery of high intensity focused ultrasound. Comput Inf Sci 7:49

    Google Scholar 

  46. 46.

    Al-hazaimeh O, Alomari SA, Alsakran J, Alhindawi N (2014) Cross correlation–new based technique for speaker recognition. Int J Acad Res 6:232–239

    Article  Google Scholar 

  47. 47.

    Bevilacqua A, Vaccari S (2007) Real time detection of stopped vehicles in traffic scenes. In: Proceedings of the 2007 IEEE conference on advanced video and signal based surveillance, September 05–07, pp 266–270. https://doi.org/10.1109/AVSS.2007.4425321

  48. 48.

    Wang X, Ma X, Grimson WEL (2008) Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models. IEEE Trans Pattern Anal Mach Intell 31:539–555

    Article  Google Scholar 

  49. 49.

    Gharaibeh N, Al-Hazaimeh OM, Al-Naami B, Nahar KM (2018) An effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images. Int J Signal Imaging Syst Eng 11:206–216

    Article  Google Scholar 

  50. 50.

    Rahim KA, Salam RA (2018) A new motion segmentation technique using foreground-background bimodal. Malays J Sci Health Technol 2:11–15

    Google Scholar 

  51. 51.

    Chen Z, Ellis T (2011) Self-adaptive Gaussian mixture model for urban traffic monitoring system. In: 2011 IEEE international conference on computer vision workshops (ICCV Workshops), pp 1769–1776

  52. 52.

    Ilyas A, Scuturici M, Miguet S (2009) Real time foreground-background segmentation using a modified codebook model. In: AVSS’09. Sixth IEEE international conference on advanced video and signal based surveillance. IEEE

Download references


This work was supported by University Science Islam Malaysia (USIM), Faculty of Engineering and Built Environment and Research and Innovation Management Center under the Research Grant Number: PPPI/FKAB/0118/051000/14618.

Author information



Corresponding author

Correspondence to Ma’moun Al-Smadi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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

Verify currency and authenticity via CrossMark

Cite this article

Al-Smadi, M., Abdulrahim, K., Seman, K. et al. A new spatio-temporal background–foreground bimodal for motion segmentation and detection in urban traffic scenes. Neural Comput & Applic 32, 9453–9469 (2020). https://doi.org/10.1007/s00521-019-04458-5

Download citation


  • Motion segmentation
  • Background subtraction
  • Cumulative frame differencing
  • Sigma–delta filter
  • Vehicle detection