Abstract
The proliferation of video cameras, such as those embedded in smartphones and wearable devices, has made it increasingly easy for users to film interesting events (such as public performance, family events, and vacation highlights) in their daily lives. Moreover, often there are multiple cameras capturing the same event at the same time, from different views. Concatenating segments of the videos produced by these cameras together along the event time forms a video mashup, which could depict the event in a less monotonous and more informative manner. It is, however, inefficient and costly to manually create a video mashup. This chapter aims to introduce the problem of automated video mashup to the readers, survey the state-of-the-art research work in this area, and outline the set of open challenges that remain to be solved. It provides a comprehensive introduction to practitioners, researchers, and graduate students who are interested in the research and challenges of automated video mashup.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that the audio and video samples captured at the same time are generated at a different time at the source due to the difference in the speed of light and the speed of sound. Humans, however, have learned to compensate for the difference in normal settings.
- 2.
See [42] for a discussion on narration, story, and events.
References
Nakano, T., Murofushi, S., Goto, M., Morishima, S.: Dancereproducer: an automatic mashup music video generation system by reusing dance video clips on the web. In: Sound and Music Computing Conference (SMC), pp. 183–189 (2011)
Fu, Y., Guo, Y., Zhu, Y., Liu, F., Song, C., Zhou, Z.H.: Multi-view video summarization. IEEE Trans. Multimedia (TOMM) 12(7), 717–729 (2010)
Pritch, Y., Ratovitch, S., Hende, A., Peleg, S.: Clustered synopsis of surveillance video. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 195–200. IEEE (2009)
Wang, X., Hirayama, T., Mase, K.: Viewpoint sequence recommendation based on contextual information for multiview video. IEEE Multimedia 22(4), 40–50 (2015)
Saini, M.K., Gadde, R., Yan, S., Ooi, W.T.: Movimash: online mobile video mashup. In: ACM International Conference on Multimedia (MM), pp. 139–148. ACM (2012)
Nguyen, D.T.D., Saini, M., Nguyen, V.T., Ooi, W.T.: Jiku director: a mobile video mashup system. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 477–478. ACM, Barcelona, Spain (2013)
Shrestha, P., Weda, H., Barbieri, M., Aarts, E.H., et al.: Automatic mashup generation from multiple-camera concert recordings. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 541–550. ACM, Firenze, Italy (2010)
Arev, I., Park, H.S., Sheikh, Y., Hodgins, J., Shamir, A.: Automatic editing of footage from multiple social cameras. ACM Trans. Grap. (TOG) 33(4), 81:1–81:11 (2014)
Su, K., Naaman, M., Gurjar, A., Patel, M., Ellis, D.P.: Making a scene: alignment of complete sets of clips based on pairwise audio match. In: Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, p. 26. ACM, Hong Kong (2012)
Sinha, S.N., Pollefeys, M.: Synchronization and calibration of camera networks from silhouettes. In: International Conference on Pattern Recognition (ICPR), pp. 116–119. IEEE (2004)
Meyer, B., Stich, T., Magnor, M.A., Pollefeys, M.: Subframe temporal alignment of non-stationary cameras. In: British Machine Vision Conference (BMVC), pp. 1–10 (2008)
Caspi, Y., Simakov, D., Irani, M.: Feature-based sequence-to-sequence matching. Int. J. Comput. Vis. (IJCV) 68(1), 53–64 (2006)
Elhayek, A., Stoll, C., Kim, K., Seidel, H., Theobalt, C.: Feature-based multi-video synchronization with subframe accuracy. Pattern Recogn. 266–275 (2012)
Hasler, N., Rosenhahn, B., Thormahlen, T., Wand, M., Gall, J., Seidel, H.P.: Markerless motion capture with unsynchronized moving cameras. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 224–231. IEEE (2009)
Kammerl, J., Birkbeck, N., Inguva, S., Kelly, D., Crawford, A.J., Denman, H., Kokaram, A., Pantofaru, C.: Temporal synchronization of multiple audio signals. In: IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP), pp. 4603–4607. IEEE, Firenze, Italy (2014)
Shrestha, P., Barbieri, M., Weda, H.: Synchronization of multi-camera video recordings based on audio. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 545–548. ACM, Augsburg, Germany (2007)
Haitsma, J., Kalker, T.: A highly robust audio fingerprinting system with an efficient search strategy. J. New Music Res. 32(2), 211–221 (2003)
Cremer, M., Cook, R.: Machine-assisted editing of user-generated content. In: IS&T/SPIE Electronic Imaging, International Society for Optics and Photonics, pp. 725,404–725,404–410 (2009)
Laiola Guimaraes, R., Cesar, P., Bulterman, D.C., Zsombori, V., Kegel, I.: Creating personalized memories from social events: community-based support for multi-camera recordings of school concerts. In: Proceedings of the 19th ACM International Conference on Multimedia, pp. 303–312. ACM, Scottdale, AZ, USA (2011)
Korchagin, D., Garner, P.N., Dines, J.: Automatic temporal alignment of av data with confidence estimation. In: IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 269–272. IEEE (2010)
Bano, S., Cavallaro, A.: Discovery and organization of multi-camera user-generated videos of the same event. Inf. Sci. 302, 108–121 (2015)
Bano, S., Cavallaro, A.: Vicomp: composition of user-generated videos. Multimedia Tools Appl. (MTAP) 75(12), 1–24 (2015)
Wu, Y., Mei, T., Xu, Y.Q., Yu, N., Li, S.: Movieup: Automatic mobile video mashup. IEEE Trans. Circ. Syst. Video Technol. 25(12), 1941–1954 (2015)
Wilk, S., Kopf, S., Effelsberg, W.: Video composition by the crowd: a system to compose user-generated videos in near real-time. In: Proceedings of the 6th ACM Multimedia Systems Conference, pp. 13–24. ACM, Portland, USA (2015)
Mei, T., Hua, X.S., Zhu, C.Z., Zhou, H.Q., Li, S.: Home video visual quality assessment with spatiotemporal factors. IEEE Trans. Circ. Syst. Video Technol. (CSVT) 17(6), 699–706 (2007)
Wilk, S., Effelsberg, W.: The influence of camera shakes, harmful occlusions and camera misalignment on the perceived quality in user generated video. In: IEEE International Conference on Multimedia and Expo (ICME). pp. 1–6. IEEE, Chengdu, China (2014)
Daniyal, F., Cavallaro, A.: Multi-camera scheduling for video production. In: Conference for Visual Media Production (CVMP), pp. 11–20. IEEE (2011)
Daniyal, F., Taj, M., Cavallaro, A.: Content and task-based view selection from multiple video streams. Multimedia Tools Appl. (MTAP) 46(2–3), 235–258 (2010)
Goshorn, R., Goshorn, J., Goshorn, D., Aghajan, H.: Architecture for cluster-based automated surveillance network for detecting and tracking multiple persons. In: ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), pp. 219–226. IEEE (2007)
Jiang, H., Fels, S., Little, J.J.: Optimizing multiple object tracking and best view video synthesis. IEEE Trans. Multimedia (TOMM) 10(6), 997–1012 (2008)
Vihavainen, S., Mate, S., Seppälä, L., Cricri, F., Curcio, I.D.: We want more: human-computer collaboration in mobile social video remixing of music concerts. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 287–296. ACM (2011)
Lerch, A.: An introduction to audio content analysis: applications in signal processing and music informatics. Wiley (2012)
Dmytyk, E.: On film editing: an introduction to the art of film construction (1984)
Canini, L., Benini, S., Leonardi, R.: Classifying cinematographic shot types. Multimedia Tools Appl. (MTAP) 62(1), 51–73 (2013)
Carlier, A., Calvet, L., Nguyen, D.T.D., Ooi, W.T., Gurdjos, P., Charvillat, V.: 3d interest maps from simultaneous video recordings. In: ACM International Conference on Multimedia, pp. 577–586. ACM (2014)
Zsombori, V., Frantzis, M., Guimaraes, R.L., Ursu, M.F., Cesar, P., Kegel, I., Craigie, R., Bulterman, D.C.: Automatic generation of video narratives from shared ugc. In: Proceedings of the 22nd ACM Conference on Hypertext and Hypermedia, pp. 325–334. ACM, Eindhoven, Netherlands (2011)
Nguyen, D.T.D., Carlier, A., Ooi, W.T., Charvillat, V.: Jiku director 2.0: a mobile video mashup system with zoom and pan using motion maps. In: Proceedings of the ACM International Conference on Multimedia, pp. 765–766. ACM, Orlando, FL, USA (2014)
Beerends, J.G., De Caluwe, F.E.: The influence of video quality on perceived audio quality and vice versa. J. Audio Eng. Soc. (AES) 47(5), 355–362 (1999)
Saini, M., Venkatagiri, S.P., Ooi, W.T., Chan, M.C.: The jiku mobile video dataset. In: ACM Multimedia Systems Conference (MMSys), pp. 108–113. ACM (2013)
Ballan, L., Brostow, G.J., Puwein, J., Pollefeys, M.: Unstructured video-based rendering: interactive exploration of casually captured videos. ACM Trans. Graphics (TOG) 29(4), 87. ACM (2010)
Park, H.S., Jain, E., Sheikh, Y.: 3D social saliency from head-mounted cameras. In: Advances in Neural Information Processing Systems (NIPS), pp. 431–439 (2012)
Nack, F.: Event and story: an intricate relationship. In: Proceedings of the 2011 Joint ACM Workshop on Modeling and Representing Events, J-MRE ’11, pp. 49–50. ACM, NY, USA (2011). https://doi.org/10.1145/2072508.2072520
Frantzis, M., Zsombori, V., Ursu, M., Guimaraes, R.L., Kegel, I., Craigie, R.: Interactive video stories from user generated content: a school concert use case. In: International Conference on Interactive Digital Storytelling, pp. 183–195. Springer, Berlin (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Definitions
Definitions
Â
- Video Mashup :
-
A video that is produced by concatenating video segments cut from input video clips recoded at the same event from different views.
- Time-Synchronized Video Mashup :
-
A video mashup that follows the same timeline as the event itself.
- Asynchronous Video Mashup :
-
A video mashup that does not follow the same timeline as the event itself, and can be shorter or longer than the actual event. An example of an asynchronous video mashup is a summary video.
- Cut point :
-
A time point in a video mashup when we choose to switch from one input video clip to another.
- Shot Length :
-
The video playback time between two cut points. In other words, the length of a video segment from the same input clip included in the video mashup.
Â
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Saini, M.K., Ooi, W.T. (2018). Automated Video Mashups: Research and Challenges. In: Montagud, M., Cesar, P., Boronat, F., Jansen, J. (eds) MediaSync. Springer, Cham. https://doi.org/10.1007/978-3-319-65840-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-65840-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65839-1
Online ISBN: 978-3-319-65840-7
eBook Packages: Computer ScienceComputer Science (R0)