Action Key Frames Extraction Using L1-Norm and Accumulative Optical Flow for Compact Video Shot Summarisation

  • Manar Abduljabbar Ahmad Mizher
  • Mei Choo AngEmail author
  • Siti Norul Huda Sheikh Abdullah
  • Kok Weng Ng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10645)


Key frame extraction is an important algorithm for video summarisation, video retrieval, and generating video fingerprint. The extracted key frames should represent a video sequence in a compact way and brief the main actions to achieve meaningful key frames. Therefore, we present a key frames extraction algorithm based on the L1-norm by accumulating action frames via optical flow method. We then evaluate our proposed algorithm using the action accuracy rate and action error rate of the extracted action frames in comparison to user extraction. The video shot summarisation evaluation shows that our proposed algorithm outperforms the-state-of-the-art algorithms in terms of compression ratio. Our proposed algorithm also achieves approximately 100% and 0.91% for best and worst case in terms of action appearance accuracy in human action dataset KTH in the extracted key frames.


L1-norm Optical flow Colour histogram Frame differences Blocks differential 


  1. 1.
    Hu, W., Xie, N., Li, L., Zeng, X., Maybank, S.: A survey on visual content-based video indexing and retrieval. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 41(6), 797–819 (2011)CrossRefGoogle Scholar
  2. 2.
    Sujatha, C., Mudenagudi, U.: A study on keyframe extraction methods for video summary. In: International Conference on Computational Intelligence and Communication Networks (CICN), pp. 73–77. IEEE (2011)Google Scholar
  3. 3.
    Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision, vol. 81, no. 1, pp. 674–679 (1981)Google Scholar
  4. 4.
    Lu, N., Wang, J., Yang, L., Wu, Q.H.: Motion detection based on accumulative optical flow and double background filtering. In: World Congress on Engineering (WCE), IWCE 2007, London, U.K., pp. 602–607. Citeseer (2007)Google Scholar
  5. 5.
    Zheng, R., Yao, C., Jin, H., Zhu, L., Zhang, Q., Deng, W.: Parallel key frame extraction for surveillance video service in a smart city. PLOS One 10, 1–8 (2015)Google Scholar
  6. 6.
    Raikwar, S.C., Bhatnagar, C., Jalal, A.S.: A framework for key frame extraction from surveillance video. In: International Conference on Computer and Communication Technology (ICCCT), Allahabad, India, pp. 297–300. IEEE (2014)Google Scholar
  7. 7.
    Sosa, J.C., Rodríguez, R., Ortega, V.H.G., Hernández, R.: Real-time optical-flow computation for motion estimation under varying illumination conditions. Int. J. Reconfigurable Embed. Syst. (IJRES) 1(1), 25–36 (2012)Google Scholar
  8. 8.
    Sheena, C.V., Narayanan, N.K.: Key-frame extraction by analysis of histograms of video frames using statistical methods. Procedia Comput. Sci. 70, 36–40 (2015)CrossRefGoogle Scholar
  9. 9.
    Thepade, S.D., Tonge, A.A.: An optimized key frame extraction for detection of near duplicates in content based video retrieval. In: International Conference on Communications and Signal Processing (ICCSP), pp. 1087–1091. IEEE (2014)Google Scholar
  10. 10.
    Cao, C., Chen, Z., Xie, G., Lei, S.: Key frame extraction based on frame blocks differential accumulation. In: 24th Chinese Control and Decision Conference (CCDC), pp. 3621–3625. IEEE (2012)Google Scholar
  11. 11.
    Mizher, M.A., Ang, M.C., Mazhar, A.A., Mizher, M.A.: A review of video falsifying techniques and video forgery detection techniques. Int. J. Electron. secur. digit. 9(3), 191–209 (2017). Publisher: Inderscience onlineGoogle Scholar
  12. 12.
    Shi, Y., Yang, H., Gong, M., Liu, X., Xia, Y. :A fast and robust key frame extraction method for video copyright protection. J. Electr. Comput. Eng. 2017, 1–7 (2017). Article no. 1231794Google Scholar
  13. 13.
    Zamani, N.A., Zahamdin, A.D.M., Abdullah, S.N.H.S., Nordin, M.J.: Sparse representation super-resolution method for enhancement analysis in video forensics. In: 12th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 921–926. IEEE (2012)Google Scholar
  14. 14.
    Schindler, K., Gool, L.V.: Action snippets: how many frames does human action recognition require? In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8. IEEE (2008)Google Scholar
  15. 15.
    Abdulameer, M.H., Abdullah, S.N.H.S., Othman, Z.A.: Support vector machine based on adaptive acceleration particle swarm optimization. Sci. World J. 2014, 1–8 (2014). Publisher: Hindawi Publishing CorporationGoogle Scholar
  16. 16.
    Claerbout, J.F., Muir, F.: Robust modeling with erratic data. Geophysics 38(5), 826–844 (1973). Publisher: Society of Exploration GeophysicistsCrossRefGoogle Scholar
  17. 17.
    Richardson, I.E.: H. 264 and MPEG-4 Video Compression: Video Coding for Next-Generation Multimedia. Wiley, Hoboken (2004)Google Scholar
  18. 18.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)CrossRefMathSciNetGoogle Scholar
  19. 19.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 3, pp. 32–36. IEEE (2004)Google Scholar
  20. 20.
    Hussein, W.A., Sahran, S., Abdullah, S.N.H.S.: A fast scheme for multilevel thresholding based on a modified bees algorithm. Knowl.-Based Syst. 101, 114–134 (2016)CrossRefGoogle Scholar
  21. 21.
    Dang, C., Radha, H.: RPCA-KFE: key frame extraction for video using robust principal component analysis. IEEE Trans. Image Process. 24(11), 3742–3753 (2015)CrossRefMathSciNetGoogle Scholar
  22. 22.
    Truong, B.T., Venkatesh, S.: Video abstraction: a systematic review and classification. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 3(1), 3 (2007)CrossRefGoogle Scholar
  23. 23.
    de Avila, S.E.F., Lopes, A.P.B., da Luz Jr., A., de Albuquerque Araújo, A.: VSUMM: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recogn. Lett. 32(1), 56–68 (2011). Publisher Elsevier B.V.CrossRefGoogle Scholar
  24. 24.
    de Avila, S.E.F., da Luz Jr., A., de Albuquerque Araújo, A., Cord, M.: VSUMM: an approach for automatic video summarization and quantitative evaluation. In: XXI Brazilian Symposium on Computer Graphics and Image Processing, Campo Grande, Brazil, pp. 103–110. IEEE (2008)Google Scholar
  25. 25.
    Vishwakarma, D.K., Rawat, P., Kapoor, R.: Human activity recognition using gabor wavelet transform and ridgelet transform. Procedia Comput. Sci. 57, 630–636 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Manar Abduljabbar Ahmad Mizher
    • 1
  • Mei Choo Ang
    • 1
    Email author
  • Siti Norul Huda Sheikh Abdullah
    • 2
  • Kok Weng Ng
    • 3
  1. 1.Institute of Visual InformaticsUniversiti Kebangsaan MalaysiaBangiMalaysia
  2. 2.Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangiMalaysia
  3. 3.Industrial Centre of Innovation in Industrial DesignSirim BerhadBukit JalilMalaysia

Personalised recommendations