Abrupt Scene Change Detection Using Spatiotemporal Regularity of Video Cube

  • Rupesh KumarEmail author
  • Sonali Ray
  • Meenakshi Sharma
  • Basant Kumar
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 587)


In this paper, we propose the detection method of abrupt scene change using spatial as well as spatiotemporal frames of video cube. Most of the methods use either intensity or motion of pixels for the scene change detection methodology. Unlike to the existing methods, both the intensity and flow vector of video frames are used simultaneously in this paper to propose a general abrupt scene change detection method. For a spatial frame, flow energy function is used for detection. Flow energy function, defined by the spatiotemporal regularity flow model, is the combinatorial form of intensity and flow vectors of the frames. In the spatio-temporal frames, abrupt scene change appears as a vertical line which is detected by the edge detection method. Combined results of spatial and the spatio-temporal frames provide the location of scene change. The proposed method detects almost all the locations of scene change with negligible false detection.


Regularity flow Video cube Flow vectors Spatiotemporal Boundary Edge detection Abrupt change 


  1. 1.
    Alatas, O., Yan, P., Shah, M.: Spatio–temporal regularity flow (SPREF): its estimation and applications. IEEE Trans. Circuits Syst. Video Technol. 17(5), 584–589 (2007). Scholar
  2. 2.
    Birinci, M., Kiranyaz, S.: A perceptual scheme for fully automatic video shot boundary detection. Signal Process.: Image Commun. 29(3), 410–423 (2014)Google Scholar
  3. 3.
    Cyganek, B., Woźniak, M.: Tensor-based shot boundary detection in video streams. New Gener. Comput. 35(4), 311–340 (2017)CrossRefGoogle Scholar
  4. 4.
    Faernando, W., Canagarajah, C., Bull, D.: Scene change detection algorithms for content-based video indexing and retrieval. Electron. Commun. Eng. J. 13(3), 117–126 (2001)CrossRefGoogle Scholar
  5. 5.
    Hong, S., Cho, B., Choe, Y.: Adaptive thresholding for scene change detection. In: IEEE Third International Conference on Consumer Electronics, pp. 75–78. IEEE (2013)Google Scholar
  6. 6.
    Huang, C.L., Liao, B.Y.: A robust scene-change detection method for video segmentation. IEEE Trans. Circuits Syst. Video Technol. 11(12), 1281–1288 (2001)CrossRefGoogle Scholar
  7. 7.
    Jang, S.W., Byun, S.: Hough transform-based robust shot change detection in digital video images. Int. Inf. Inst. (Tokyo), Inf. 20(2B), 1245 (2017)Google Scholar
  8. 8.
    Kang, S.J.: Adaptive luminance coding-based scene-change detection for frame rate up-conversion. IEEE Trans. Consum. Electron. 59(2), 370–375 (2013)CrossRefGoogle Scholar
  9. 9.
    Kang, S.J., Cho, S.I., Yoo, S., Kim, Y.H.: Scene change detection using multiple histograms for motion-compensated frame rate up-conversion. J. Disp. Technol. 8(3), 121–126 (2012)CrossRefGoogle Scholar
  10. 10.
    Koprinska, I., Carrato, S.: Temporal video segmentation: a survey. Signal Process.: Image Commun. 16(5), 477–500 (2001)Google Scholar
  11. 11.
    Li, H., Liu, G., Zhang, Z., Li, Y.: Adaptive scene-detection algorithm for VBR video stream. IEEE Trans. Multimed. 6(4), 624–633 (2004)CrossRefGoogle Scholar
  12. 12.
    Majumdar, J., Aniketh, M., Abhishek, B., Hegde, N.: Video shot detection in transform domain. In: 2nd International Conference for Convergence in Technology (I2CT), pp. 161–168. IEEE (2017)Google Scholar
  13. 13.
    Prabavathy, A.K., Shree, J.D.: Histogram difference with fuzzy rule base modeling for gradual shot boundary detection in video cloud applications. Clust. Comput. 1–8 (2017)Google Scholar
  14. 14.
    Rosin, P.L., Ioannidis, E.: Evaluation of global image thresholding for change detection. Pattern Recognit. Lett. 24(14), 2345–2356 (2003)CrossRefGoogle Scholar
  15. 15.
    Rupesh, K., Gupta, S., Venkatesh, K.S.: Cut scene change detection using spatio temporal video frame. In: International Conference on Image Information Processing (ICIIP) (2015)Google Scholar
  16. 16.
    Shen, R.K., Lin, Y.N., Juang, T.T.Y., Shen, V.R., Lim, S.Y.: Automatic detection of video shot boundary in social media using a hybrid approach of HLFPN and keypoint matching. IEEE Trans. Comput. Soc. Syst. 5(1), 210–219 (2018)CrossRefGoogle Scholar
  17. 17.
  18. 18.
    Youm, S., Kim, W.: Dynamic threshold method for scene change detection. In: International Conference on Multimedia and Expo, ICME’03, vol. 2, pp. II–337. IEEE (2003)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.IITKanpurIndia
  2. 2.MNNITAllahabadIndia

Personalised recommendations