Abstract
This paper presents a novel technique for classifying several camera operations in videos. First of all, we obtain a series of 2D motion vector (MV) fields by applying an existing MV estimation method. Then, a 2D MV histogram is generated in polar coordinates. The histogram shows that how many MVs in each frame share the similar magnitude and orientation. These two MV features are utilized simultaneously to classify the camera operations by representing on the 2D histogram. The proposed method can detect not only single camera operations but also a combination of two camera operations. The 2D histogram can describe the speed of the camera operations. Moreover, the 2D MV field itself can separate zoom-in and zoom-out camera operations that may produce exactly the same pattern in the 2D MV histogram. Especially, separating zoom-in and zoom-out camera operations because these two operations produce a similar 2D histogram. The proposed method can achieve a processing time of 5-10 millisecond per frame for a low-resolution video, while it takes 40-80 millisecond for a high-resolution video.
Similar content being viewed by others
References
Abdollahian G, Taskiran CM, Pizlo Z, Delp EJ (2010) Camera motion-based analysis of user generated video. IEEE Transactions on Multimedia 12(1):28–41
Almeida J, Minetto R, Almeida TA, Torres RS, Leite NJ (2010) Estimation of camera parameters in video sequences with a large amount of scene motion. In: 2010 17th International conference on systems, signals and image processing (IWSSIP 2010), pp 348–358
Bendraou Y, Essannouni F, Aboutajdine D, Salam A (2014) Video shot boundary detection method using histogram differences and local image descriptor. In: 2014 Second world conference on complex systems (WCCS), pp 665–670
Block matching algorithms for motion estimation. https://www.mathworks.com/matlabcentral/fileexchange/8761-block-matching-algorithms-for-motion-estimation. Accessed 04 Apr 2018
Chen Y, Zhang L, Lin B, Xu Y, Ren X (2011) Fighting detection based on optical flow context histogram. In: 2011 Second international conference on innovations in bio-inspired computing and applications, pp 95–98
de Souza TT, Goularte R (2013) Video shot representation based on histograms. In: Proceedings of the 28th annual ACM symposium on applied computing SAC ’13. ACM, New York, pp 961–966
Derue FX, Dahmane M, Lalonde M, Foucher S (2017) Exploiting semantic segmentation for robust camera motion classification. In: Image analysis and recognition, pp 173–181
Duan LY, Jin JS, Tian Q, Xu CS (2006) Nonparametric motion characterization for robust classification of camera motion patterns. IEEE Trans Multimed 8(2):323–340
Erturk S (2003) Digital image stabilization with sub-image phase correlation based global motion estimation. IEEE Trans Consum Electron 49(4):1320–1325
Experimental data of duan’s method and okade’s method. http://www.facweb.iitkgp.ernet.in/~pkb/camera_classify.html. Accessed 04 Apr 2018
Ewerth R, Schwalb M, Tessmann P, Freisleben B (2004) Estimation of arbitrary camera motion in mpeg videos. In: Proceedings of the 17th international conference on pattern recognition, 2004. ICPR 2004, vol 1, pp 512–515
Fakhar B, Kanan HR, Behrad A (2019) Event detection in soccer videos using unsupervised learning of spatio-temporal features based on pooled spatial pyramid model. Multimed Tools Appl 78(12):16995–17025
Gonzalez RC, Woods RE (2006) Digital image processing, 3rd edn. Prentice-Hall, Inc., Upper Saddle River
Hasan MA, Xu M, He X, Xu C (2014) Camhid: camera motion histogram descriptor and its application to cinematographic shot classification. IEEE Trans Circ Syst Video Technol 24(10):1682–1695
Hasan MA, Xu M, He X, Wang Y (2015) A camera motion histogram descriptor for video shot classification. Multimed Tools Appl 74(24):11073–11098
Hu WC, Chen CH, Chen TY, Peng MY, Su YJ (2018) Real-time video stabilization for fast-moving vehicle cameras. Multimed Tools Appl 77(1):1237–1260
Kim JG, Chang HS, Kim J, Kim HM (2000) Efficient camera motion characterization for mpeg video indexing. In: 2000 IEEE International conference on multimedia and expo. ICME2000. Proceedings. Latest advances in the fast changing world of multimedia (Cat. No.00TH8532), vol 2, pp 1171– 1174
Lee S, Hayes MH (2002) Real-time camera motion classification for content-based indexing and retrieval using templates. In: 2002 IEEE International conference on acoustics, speech, and signal processing, vol 4, pp IV–3664–IV–3667
Luca C, Sergio B, Riccardo L (2013) Classifying cinematographic shot types. Multimed Tools Appl 62(1):51–73
Mahabalagiri A, Ozcan K, Velipasalar S (2014) Camera motion detection for mobile smart cameras using segmented edge-based optical flow. In: 2014 11th IEEE International conference on advanced video and signal based surveillance (AVSS), pp 271–276
Matlab the language of technical computing. https://www.mathworks.com. Accessed 04 Apr 2018
Mpeg the moving picture experts group website. https://mpeg.chiariglione.org/. Accessed 13 Aug 2019
Narayanan S, Makur A (2013) Camera motion estimation using circulant compressive sensing matrices. In: 2013 9th International conference on information, communications signal processing, pp 1–5
Nguyen NT, Laurendeau D, Branzan-Albu A (2010) A robust method for camera motion estimation in movies based on optical flow. Int J Intell Syst Technol Appl 9(3/4):228–238
Nie Y, Ma KK (2002) Adaptive rood pattern search for fast block-matching motion estimation. IEEE Trans Image Process 11(12):1442–1449
Nikitidis S, Zafeiriou S, Pitas I (2008) Camera motion estimation using a novel online vector field model in particle filters. IEEE Trans Circ Syst Vid Technol 18(8):1028–1039
Okade M, Biswas PK (2012) Fast camera motion estimation using discrete wavelet transform on block motion vectors. In: 2012 Picture coding symposium, pp 333–336
Okade M, Patel G, Biswas PK (2016) Robust learning-based camera motion characterization scheme with applications to video stabilization. IEEE Trans Circ Syst Vid Technol 26(3):453–466
Patel NV, Sethi IK (1997) Video shot detection and characterization for video databases. Pattern Recogn 30(4):583–592
Prasertsakul P (2018) A video analysis for camera motion estimation and its application to automatic retrieval of attractive moments in sport videos. Dissertation, Japan Advanced Institute of Science and Technology
Prasertsakul P, Kondo T, Iida H (2017) Video shot classification using 2d motion histogram. In: 2017 14th International conference on electrical engineering/electronics, computer, telecommunications and information technology (ECTI-CON), pp 202–205
Puthenpurayil SP, Chakrabarti I, Virdi R, Kaushik H (2016) Very large scale integration architecture for block-matching motion estimation using adaptive rood pattern search algorithm. IET Circ Dev Syst 10(4):309–316
Shih H (2013) A novel attention-based key-frame determination method. IEEE Trans Broadcast 59(3):556–562
Spampinato G, Bruna A, Naccari F, Tomaselli V (2019) Adaptive low cost algorithm for video stabilization. Multimed Tools Appl 78(10):13787–13804
Srinivasan M, Venkatesh S, Hosie R (1997) Qualitative estimation of camera motion parameters from video sequences. Pattern Recogn 30(4):593–606
Tan YP, Saur DD, Kulkami SR, Ramadge PJ (2000) Rapid estimation of camera motion from compressed video with application to video annotation. IEEE Trans Circ Syst Video Technol 10(1):133–146
Tavassolipour M, Karimian M, Kasaei S (2014) Event detection and summarization in soccer videos using Bayesian network and copula. IEEE Trans Circ Syst Video Technol 24(2):291–304
Tu Y, Zhang X, Liu B, Yan C (2017) Video description with spatial-temporal attention. In: Proceedings of the 25th ACM international conference on multimedia, pp 1014–1022
Ultra video group. http://ultravideo.cs.tut.fi/#testsequences. Accessed 15 Aug 2018
Video samples. http://www.divx.com/en/devices/profiles/video. Accessed 04 Apr 2018
Wang R, Huang T (1999) Fast camera motion analysis in mpeg domain. In: Proceedings 1999 international conference on image processing (Cat. 99CH36348), vol 3, pp 691–694
Weng Y, Jiang J (2011) Fast camera motion estimation in mpeg compressed domain. IEEE Trans Consum Electron 57(3):1329–1335
Xiph.org video test media [derf’s collection]. https://media.xiph.org/video/derf/. Accessed 04 Apr 2018
Xiao Q, Wang H, Li F, Gao Y (2011) 3d object retrieval based on a graph model descriptor. Neurocomputing 74(17):3486–3493
Xiao Q, Luo Y, Wang H (2014) Motion retrieval based on switching Kalman filters model. Multimed Tools Appl 72(1):951–966
Xiao Q, Wang Y, Wang H (2015) Motion retrieval using weighted graph matching. Soft Comput 19(1):133–144
Yan C, Tu Y, Wang X, Zhang Y, Hao X, Zhang Y, Dai Q (2019) Stat: spatial-temporal attention mechanism for video captioning. IEEE Trans Multimed (Early Access), 1–1
Yu J, Tao D, Wang M, Rui Y (2015) Learning to rank using user clicks and visual features for image retrieval. IEEE Trans Cybern 45(4):767–779
Zhang L, Xu QK, Nie LZ, Huang H (2014) Videograph: a non-linear video representation for efficient exploration. Vis Comput 30(10):1123–1132
Zhu X, Elmagarmid AK, Xue X, Wu L, Catlin AC (2005) Insightvideo: toward hierarchical video content organization for efficient browsing, summarization and retrieval. IEEE Trans Multimed 7(4):648–666
Acknowledgements
This research is financially supported by Sirindhorn International Institute of Technology (SIIT), Thammasat University (TU), Japan Advanced Institute of Science and Technology (JAIST), National Science and Technology Development Agency (NSTDA), and National Research University Project (NRU), Thailand Office of Higher Education Commission.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Prasertsakul, P., Kondo, T., Iida, H. et al. Camera operation estimation from video shot using 2D motion vector histogram. Multimed Tools Appl 79, 17403–17426 (2020). https://doi.org/10.1007/s11042-019-08378-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08378-3