Soft Computing

, Volume 23, Issue 21, pp 10661–10679 | Cite as

CBFD: a refined W4+ cluster-based frame difference approach for efficient moving object detection

  • T. MahalingamEmail author
  • M. Subramoniam


Nowadays, automated object detection and tracking is needed for video observation, robotic control, and vehicle driver aid systems. Object detection and tracking is an essential, complex activity in PC system vision due to the challenges in tracking. Continual contortion of objects at that time of motion and background scatter causes inadequate tracking. Non-static objects can be efficiently identified by deviation between the frames and clustering techniques, yet background system need to be upgraded consistently, and it is also vulnerable to camera jitter and lighting variants. In order to overcome these issues, an effective cluster-based frame differencing and W4+ method is proposed. These methods are helping to efficiently recognize the non-static object, in which a single technique cannot provide an efficient result. The proposed refined W4+ incorporated with CBFD method is used to detect the efficient moving object detection during the image analysis process. In addition to that, the fuzzy morphological filter processing to reduce the noise drastically. The objects with various sizes, contours, and lighting variants are available in the dataset, which makes the assessment of data a difficult task. The speculative outcomes and efficiency analysis on real video series datasets illustrate the efficiency of our strategies in contrast with existing strategies.


Non-static object detection Background subtraction Frame distinction Cluster-based frame difference (CBFD) Threshold Morphology W4+ 


Author’s contribution

TM contributed to technical and conceptual content, architectural design. MS contributed to guidance and counselling on the writing of the paper.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Human and animal rights

There is no animal involvement in this research.

Informed consent

The authors declare that they have no consent.


  1. Abualigah LMQ (2019) Feature selection and enhanced krill herd algorithm for text document clustering. In: Studies in Computational Intelligence book series.
  2. Abualigah LM, Khader AT (2017) Unsupervised text feature selection technique based on hybrid particle swarm optimization algorithm with genetic operators for the text clustering. J Supercomput 73(11):4773–4795CrossRefGoogle Scholar
  3. Abualigah LM, Khader AT, Al-Betar MA, Awadallah MA (2016a) A krill herd algorithm for efficient text documents clustering. In: IEEE symposium on computer applications and industrial electronics (ISCAIE), pp 67–72Google Scholar
  4. Abualigah LM, Khader AT, Al-Betar MA (2016b) Multi-objectives-based text clustering technique using K-mean algorithm. In: Computer science and information technology (CSIT). IEEE, pp 1–6Google Scholar
  5. Abualigah LM, Khader AT, Al-Betar MA (2016c) Unsupervised feature selection technique based on genetic algorithm for improving the text clustering. In: Computer science and information technology (CSIT). IEEE, pp 1–6Google Scholar
  6. Abualigah LM, Khader AT, Al-Betar MA, Alomari OA (2017a) Text feature selection with a robust weight scheme and dynamic dimension reduction to text document clustering. Expert Syst Appl 84:24–36CrossRefGoogle Scholar
  7. Abualigah LM, Khader AT, Al-Betar MA, Hanandeh ES (2017b) A new hybridization strategy for krill herd algorithm and harmony search algorithm applied to improve the data clustering. In: 1st EAI international conference on computer science and engineering.
  8. Abualigah LM, Khader AT, Hanandeh ES, Gandomi AH (2017c) A novel hybridization strategy for krill herd algorithm applied to clustering techniques. Appl Soft Comput 60:423–435CrossRefGoogle Scholar
  9. Abualigah LM, Khader AT, Hanandeh ES (2018a) A hybrid strategy for krill herd algorithm with harmony search algorithm to improve the data clustering. Intell Decis Technol 12(1):3–14CrossRefGoogle Scholar
  10. Abualigah LM, Khader AT, Hanandeh ES (2018b) Hybrid clustering analysis using improved Krill herd algorithm. Appl Intell 48(11):4047–4071CrossRefGoogle Scholar
  11. Abualigah LM, Khader AT, Hanandeh ES (2018c) A combination of objective functions and hybrid Krill herd algorithm for text document clustering analysis. Eng Appl Artif Intell 73:111–125CrossRefGoogle Scholar
  12. Barnich O, Droogenbroeck MV (2009) Vibe: a powerful random technique to estimate the background in video sequences. In: Proceedings of the international conference on acoustics, speech, and signal processing, pp 945–948.
  13. Barnich O, Droogenbroeck MV (2011) Vibe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709–1724. MathSciNetCrossRefzbMATHGoogle Scholar
  14. Benezeth Y, Jodoin P, Emile B, Laurent H, Rosenberger C (2008) Review and evaluation of commonly-implemented background subtraction algorithms. In: Proceedings of the international conference on pattern recognition. IEEE, pp 1–4.
  15. Candamo J, Shreve M, Goldgof D, Sapper D, Kasturi R (2010) Understanding transit scenes: a survey on human behavior recognition algorithms. IEEE Trans Intell Transp Syst 11(1):206–224CrossRefGoogle Scholar
  16. Cristani M, Farenzena M, Bloisi D, Murino V (2010) Background subtraction for automated multi sensor surveillance: a comprehensive review. EURASIP J Adv Signal Process 1:24. CrossRefGoogle Scholar
  17. Dou J, Qin Q, Tu Z (2017) Background subtraction based on circulant matrix. Signal Image Video Process 11(3):407–414CrossRefGoogle Scholar
  18. Garcia J, Gardel A, Bravo I, Lazaro J, Martinez M, Rodriguez D (2013) Directional people counter based on head tracking. IEEE Trans Ind Electron 60(9):3991–4000CrossRefGoogle Scholar
  19. Ghosh A, Subudhi BN, Ghosh S (2012) Object detection from videos captured by moving camera by fuzzy edge incorporated markov random field and local histogram matching. IEEE Trans Circuits Syst Video Technol 22(8):1127–1135. CrossRefGoogle Scholar
  20. Gupta SK, Agrwal SL, Meena YK, Nain N (2011) A hybrid method of feature extraction for facial expression recognition. In: Proceedings of the 7th international conference on signal-image technology and internet-based systems (SITIS). IEEE, pp 422–425.
  21. Hosaka T, Kobayashi T, Otsu N (2011) Object detection using background subtraction and foreground motion estimation. IPSJ Trans Comput Vis Appl 3:9–20. CrossRefGoogle Scholar
  22. Hu WC, Chen CH, Chen CM, Chen TY (2014) Effective moving object detection from videos captured by a moving camera. In: Proceedings of the Euro-China conference on intelligent data analysis and applications, vol 1, pp 343–353.
  23. Kavitkar AV, Sarkar Pradeep Ingle AV (2014) Human and moving object detection and tracking using image processing. Int J Eng Tech Res 2(3):186–189Google Scholar
  24. Khan MAM (2001) Fast distance metric based data mining techniques using p-trees: k-nearest-neighbor classification and k-clustering. A thesis submitted to the graduate faculty of the North Dakota State UniversityGoogle Scholar
  25. Ko T, Soatto S, Estrin D (2008) Background subtraction on distributions. In: Computer vision-ECCV, lecture notes in computer science, vol 5304, pp 276–289.
  26. Kolmogorov V, Criminisi A, Blake A, Cross G, Rother C (2006) Probabilistic fusion of stereo with color and contrast for bi-layer segmentation. IEEE Trans Pattern Anal Mach Intell 28(9):1480–1492. CrossRefzbMATHGoogle Scholar
  27. Lan Y, Ji Z, Gao J, Yaowei W (2014) Robot fish detection based on a combination method of three frame-difference and background subtraction. In: Proceedings of the 26th Chinese control and decision conference (2014 CCDC). IEEE, pp 3905–3909.
  28. Li L, Huang W, Gu I, Tian Q (2003) Foreground object detection from videos containing complex background. In: Proceedings of the multimedia 11th ACM international conference, Berkeley, USA, pp 2–10.
  29. Li L, Huang WM, Gu IH, Tian Q (2004) Statistical modelling of complex background for foreground object detection. IEEE Trans Image Process 13(11):1459–1472. CrossRefGoogle Scholar
  30. Mahalingam T, Subramoniam M (2018) A robust single and multiple moving object detection, tracking and classification. Appl Comput Inform. CrossRefGoogle Scholar
  31. Mahraz MA, Riffi J, Tairi H (2015) High accuracy optical flow estimation based on PDE decomposition. Signal Image Video Process 9(6):1409–1418CrossRefGoogle Scholar
  32. Matteucci M (2008) A tutorial on clustering algorithms (online).
  33. Megrhi S, Jmal M, Souidene W, Beghdadi A (2016) Spatio-temporal action localization and detection for human action recognition in big dataset. J Vis Commun Image Represent 41:375–390CrossRefGoogle Scholar
  34. Motlagh O, Nakhaeinia D, Tang SH, Karasfi B, Khaksar W (2014) Automatic navigation of mobile robots in unknown environments. J Neural Comput Appl 24(7):1569–1581CrossRefGoogle Scholar
  35. Ortega JP, Rocío Boone Rojas MD, Somodevilla García MJ (2009) Research issues on K-means algorithm: an experimental trial using Matlab. In: CEUR workshop proceedings: semantic web and new technologies, pp 83–96.
  36. Sanchez A, Nunes E, Conci A (2012) Using adaptive background subtraction into a multilevel model for traffic surveillance. J Integr Comput Aided Eng 19(3):239–256CrossRefGoogle Scholar
  37. Sengar SS, Mukhopadhyay S (2016a) Moving object area detection using normalized self adaptive optical flow. Opt Int J Light Electron Opt 127(16):6258–6267CrossRefGoogle Scholar
  38. Sengar SS, Mukhopadhyay S (2016b) A novel method for moving object detection based on block based frame differencing. In: 3rd IEEE international conference on recent advances in information technology, pp 462–472Google Scholar
  39. Sengar SS, Mukhopadhyay S (2017a) Moving object detection based on frame difference and W4. SIViP 11(7):1357–1364. CrossRefGoogle Scholar
  40. Sengar SS, Mukhopadhyay S (2017b) Foreground detection via background subtraction and improved three-frame differencing. Arab J Sci Eng. CrossRefGoogle Scholar
  41. Sharma U, Sharma T, Jain T (2015) Efficient object detection with its enhancement. In: Proceedings of the computing communication and automation (ICCCA). IEEE, pp 1096–1099.
  42. Singh A, Yadav A, Rana A (2013) K-means with three different distance metrics. Int J Comput Appl. CrossRefGoogle Scholar
  43. Singla N (2014) Motion detection based on frame difference method. Int J Inf Comput Technol 4(15):1559–1565Google Scholar
  44. Sobral A, Vacavant A (2014) A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput Vis Image Underst 122:4–21CrossRefGoogle Scholar
  45. Soni K, Gupta SK, Kumar U, Agrwal SL (2014) A new Gabor wavelet transform feature extraction technique for ear biometric recognition. In: Proceedings of the 6th power India international conference (PIICON), 2014. IEEE, pp 1–3.
  46. Verma D, Dhaka V, Agrwal S (2013) An improved average Gabor wavelet filter feature extraction technique for facial expression recognition. Int J Innov Eng Technol 2(4):35–41.Google Scholar
  47. Wang Y (2010) Joint random field model for all-weather moving vehicle detection. IEEE Trans Image Process 19(9):2491–2501. MathSciNetCrossRefzbMATHGoogle Scholar
  48. Wolf C, Jolion JM (2010) Integrating a discrete motion model into GMM based background subtraction. In: Proceedings of the 20th IEEE international conference on pattern recognition, pp 9–12.
  49. Yang J, Yang W, Li M (2012) An efficient moving object detection algorithm based on improved GMM and cropped frame technique. In: Proceedings of IEEE international conference on the mechatronics and automation, pp 658–663.
  50. Yin J, Liu L, Li H, Liu Q (2016) The infrared moving object detection and security detection related algorithms based on w4 and frame difference. Infrared Phys Technol 77:302–315. CrossRefGoogle Scholar
  51. Zhang X, Yang J (2008) Foreground segmentation based on selective foreground model. IEEE Electron Lett 44(14):851–852. CrossRefGoogle Scholar
  52. Zhang W, Fang XZ, Yang X (2006) Moving vehicles segmentation based on Bayesian framework for Gaussian motion model. Pattern Recognit Lett 27(9):956–967. CrossRefGoogle Scholar
  53. Zhang Y, Wang X, Biao Q (2012) Three-frame difference algorithm research based on mathematical morphology. Procedia Eng 29:2705–2709. CrossRefGoogle Scholar
  54. Zhang R, Liu X, Hu J, Chang K, Liu K (2016) A fast method for moving object detection in video surveillance image. Signal Image Video Process 11(5):1–8Google Scholar
  55. Zhao N, Xia Y, Xu C, Shi X, Liu Y (2016) APPOS: an adaptive partial occlusion segmentation method for multiple vehicles tracking. J Vis Commun Image Represent 37:25–31CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Sathyabama UniversityChennaiIndia

Personalised recommendations