Applied Intelligence

, Volume 49, Issue 3, pp 1146–1160 | Cite as

A new block matching algorithm based on stochastic fractal search

  • Abir BetkaEmail author
  • Nadjiba Terki
  • Abida Toumi
  • Madina Hamiane
  • Amina Ourchani


Block matching algorithm is the most popular motion estimation technique, due to its simplicity of implementation and effectiveness. However, the algorithm suffers from a long computation time which affects its general performance. In order to achieve faster motion estimation, a new block matching algorithm based on stochastic fractal search, SFS, is proposed in this paper. SFS is a metaheuristic technique used to solve hard optimization problems in minimal time. In this work, two main contributions are presented. The first one consists of computing the motion vectors in a parallel structure as opposed to the other hierarchical metaheuristic block matching algorithms. When the video sequence frame is divided into blocks, a multi-population model of SFS is used to estimate the motion vectors of all blocks simultaneously. As a second contribution, the proposed algorithm is modified in order to enhance the results. In this modified version, four ideas are investigated. The random initialization, usually used in metaheuristics, is replaced by a fixed pattern. The initialized solutions are evaluated using a new fitness function that combines two matching criteria. The considered search space is controlled by a new adaptive window size strategy. A modified version of the fitness approximation method, which is known to reduce computation time but causes some degradation in the estimation accuracy, is proposed to balance between computation time and estimation accuracy. These ideas are evaluated in nine video sequences and the percentage improvement of each idea, in terms of estimation accuracy and computational complexity, is reported. The presented algorithms are then compared with other well-known block matching algorithms. The experimental results indicate that the proposed ideas improve the block matching performance, and show that the proposed algorithm outperforms many state-of-the-art methods.


Block matching algorithm Motion estimation Stochastic fractal search Metaheuristics 


  1. 1.
    Fortun D, Bouthemy P, Kervrann C (2015) Optical flow modeling and computation: a survey. Comput Vis Image Underst 134:1–21zbMATHGoogle Scholar
  2. 2.
    Ilg E, Mayer N, Saikia T, et al. (2016) Flownet 2.0: Evolution of optical flow estimation with deep networks. arXiv:1612.01925
  3. 3.
    Chen Q, Koltun V (2016) Full flow: Optical flow estimation by global optimization over regular grids. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4706–4714Google Scholar
  4. 4.
    Palomares RP, Meinhardt-Llopis E, Ballester C, ohers (2017) FALDOI: A new minimization strategy for large displacement variational optical flow. J Math Imaging Vision 58(1):27–46Google Scholar
  5. 5.
    Horn BKP, Schunck BG (1981) Determining optical flow. Artif Intell 17(1–3):185–203Google Scholar
  6. 6.
    Metkar S, Talbar S (2013) Performance evaluation of block matching algorithms for video coding. In: Motion estimation techniques for digital video coding. Springer, India, pp 13–31Google Scholar
  7. 7.
    Furht B, Greenberg J, Westwater R (2012) Motion estimation algorithms for video compression. Springer Science, Business MediaGoogle Scholar
  8. 8.
    Terki N, Saigaa D, Cheriet L, et al. (2013) Fast motion estimation algorithm based on complex wavelet transform. Journal of Signal Processing Systems 72(2):99–105Google Scholar
  9. 9.
    Barjatya A (2004) Block matching algorithms for motion estimation. IEEE Trans Evol Comput 8(3):225–239Google Scholar
  10. 10.
    Choudhury HA, Saikia M (2014) Survey on block matching algorithms for motion estimation. In: 2014 international conference on communications and signal processing (ICCSP). IEEE, pp 036–040Google Scholar
  11. 11.
    Li S, Xu W-P, Wang H, et al. (1999) A novel fast motion estimation method based on genetic algorithm. In: 1999 international conference on image processing, 1999. ICIP 99. Proceedings. IEEE, pp 66–69Google Scholar
  12. 12.
    Ren R, Shi Y, Zheng B, et al. (2006) A fast block matching algorithm for video motion estimation based on particle swarm optimization and motion prejudgment. arXiv:cs/0609131
  13. 13.
    Cai J, Pan WD (2012) On fast and accurate block-based motion estimation algorithms using particle swarm optimization. Inf Sci 197:53–64Google Scholar
  14. 14.
    Yuan X, Shen X (2008) Block matching algorithm based on particle swarm optimization for motion estimation. In: International conference on embedded software and systems, 2008. ICESS’08. IEEE, pp 191–195Google Scholar
  15. 15.
    Cuevas E, Zaldivar D, Pérez-Cisneros M, et al. (2013) Block-matching algorithm based on differential evolution for motion estimation. Eng Appl Artif Intell 26(1):488–498Google Scholar
  16. 16.
    Díaz-Cortés M-A, Cuevas E, Rojas R (2017) Motion estimation algorithm using block-matching and harmony search optimization. In: Engineering applications of soft computing. Springer International Publishing, pp 13–44Google Scholar
  17. 17.
    Damerchilu B, Norouzzadeh MS, Meybodi MR (2016) Motion estimation using learning automata. Mach Vis Appl 27(7):1047–1061Google Scholar
  18. 18.
    Zhang J, Wang C, Zhou M (2015) Fast and epsilon-optimal discretized pursuit learning automata. IEEE Transactions on Cybernetics 45(10):2089–2099Google Scholar
  19. 19.
    Salimi H (2015) Stochastic fractal search: a powerful metaheuristic algorithm. Knowl-Based Syst 75:1–18Google Scholar
  20. 20.
    Chuan SUN, Wei Z-Q, Zhou C-J, et al. (2016) Stochastic fractal search algorithm for 3d protein structure prediction. DEStech Transactions on Computer Science and Engineering, no aicsGoogle Scholar
  21. 21.
    Rahman TAZ (2016) Parameters optimization of an SVM-classifier using stochastic fractal search algorithm for monitoring an aerospace structureGoogle Scholar
  22. 22.
    Sivalingam R, Chinnamuthu S, Dash SS (2017) A hybrid stochastic fractal search and local unimodal sampling based multistage PDF plus (1 + PI) controller for automatic generation control of power systems. Journal of the Franklin InstituteGoogle Scholar
  23. 23.
    Parejo Maestre JA, Ruiz Cortés A, Lozano Segura S, et al. (2012) Metaheuristic optimization frameworks: a survey and benchmarking. Soft Comput 16(3):1–35Google Scholar
  24. 24.
    Boussaïd I, Lepagnot J, Siarry P (2013) A survey on optimization metaheuristics. Inf Sci 237:82–117MathSciNetzbMATHGoogle Scholar
  25. 25.
    Deviant S. (2011) The practically cheating statistics handbook–.
  26. 26.
    Goshtasby AA (2012) Image registration: principles, tools and methods. Springer Science, Business MediazbMATHGoogle Scholar
  27. 27.
    Smith SW, et al. (1997) The scientist and engineer’s guide to digital signal processingGoogle Scholar
  28. 28.
    Feng J, Lo K-T, Mehrpour H, et al. (1995) Adaptive block matching motion estimation algorithm for video coding. Electron Lett 31(18):1542–1543Google Scholar
  29. 29.
    Oh H-S, Park G, Lee H-K (1997) Block-matching algorithm based on dynamic search window adjustment. Dept. of CS, KAISTGoogle Scholar
  30. 30.
    Li W, Salari E (1995) Successive elimination algorithm for motion estimation. IEEE Trans Image Process 4(1):105–107Google Scholar
  31. 31.
    Jong H-M, Chen L-G, Chiueh T-D (1994) Accuracy improvement and cost reduction of 3-step search block matching algorithm for video coding. IEEE Trans Circuits Syst Video Technol 4(1):88–90Google Scholar
  32. 32.
    Li R, Zeng B, Liou ML (1994) A new three-step search algorithm for block motion estimation. IEEE Trans Circuits Syst Video Technol 4(4):438–442Google Scholar
  33. 33.
    Lu J, Liou ML (1997) A simple and efficient search algorithm for block-matching motion estimation. IEEE Trans Circuits Syst Video Technol 7(2):429–433Google Scholar
  34. 34.
    Po L-M, Ma W-C (1996) A novel four-step search algorithm for fast block motion estimation. IEEE Trans Circuits Syst Video Technol 6(3):313–317Google Scholar
  35. 35.
    Zhu S, Ma K-K (1997) A new diamond search algorithm for fast block matching motion estimation. In: Proceedings of 1997 international conference on information, communications and signal processing, 1997. ICICS. IEEE, pp 292–296Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Abir Betka
    • 1
    Email author
  • Nadjiba Terki
    • 1
  • Abida Toumi
    • 1
  • Madina Hamiane
    • 2
  • Amina Ourchani
    • 1
  1. 1.Department of Electrical EngineeringUniversity of Biskra AlgeriaBiskraAlgeria
  2. 2.Department of Telecommunication EngineeringAhlia UniversityManamaBahrain

Personalised recommendations