Abstract
In a Content-based Video Retrieval system, the shot boundary detection is an unavoidable stage. Such a high demanding task needs a deep study from a computational point of view to allow finding suitable optimization strategies. This paper presents different strategies implemented on both a shared-memory symmetric multiprocessor and a Beowulf cluster, and the evaluation of two different programming paradigms: shared-memory and message passing. Several approaches for video segmentation as well as data access are tested in the experiments that also consider load balancing issues.
Similar content being viewed by others
Notes
From now on there will be no difference on the use of the terms thread and process.
The speedup for each implementation is calculated as the ratio between the time obtained when using a single processor and the time with N processors.
References
Antani S, Kasturi R, Jain R (2002) A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video. Pattern Recognit 35(4):945–965
Bell G, Gray J (2002) What’s next in high-performance computing? Commun ACM 45(2):91–95
Bosque JL, Robles OD, Pastor L, Rodríguez A (2006) Parallel CBIR implementations with load balancing algorithms. J Parallel Distrib Comput 66(8):1062–1075
Gustafson JL (1988) Reevaluating Amdahl’s law? Commun ACM 31(5):532–533
Joyce RA, Liu B (2006) Temporal segmentation of video using frame and histogram space. IEEE Trans Multimed 8(1):130–140
Marques O, Furht B (2002) Content-based image and video retrieval. In: Multimedia systems and application series. Kluwer Academic, Dordrecht
Robles OD, Toharia P, Rodríguez A, Pastor L (2004) Towards a content-based video retrieval system using wavelet-based signatures. In: Hamza MH (ed) 7th IASTED international conference on computer graphics and imaging, CGIM2004, Kauai, Hawaii, EEUU, August 2004. IASTED ACTA Press, Anaheim, pp 344–349
Sebe N, Lew MS, Smeulders AWM (2003) Video retrieval and summarization. Comput Vis Image Underst 92(2–3):141–146
Smeaton AF (2003) TRECVID 2003 video evaluation overview. TRECVID 2003 conference, National Institute for Standards and Technology. http://www-nlpir.nist.gov/projects/tvpubs/tvpapers03/tv3.overview.slides.pdf
Toharia P, Robles OD, Rodríguez A, Pastor L (2007) A study of Zernike invariants for content-based image retrieval. In: Proceedings of the IEEE pacific rim symposium on image video and technology, PSIVT2007, Chile, December 2007. Lecture notes on computer science, vol 4872. IEEE Press/Springer, New York/Berlin, pp 944–957
Valencia G, Rodríguez JA, Urdiales C, Sandoval F (2004) Color-based video segmentation using interlinked irregular pyramids. Pattern Recognit 37(2):377–380
Zhang D, Qi W, Zhang HJ (2001) A new shot boundary detection algorithm. In: Shum H-Y, Liao M, Chang S-F (eds) IEEE Pacific Rim conference on multimedia, vol 2195. IEEE Press/Springer, New York/Berlin, pp 63–70
Acknowledgements
This work has been partially funded by the Spanish Ministry of Education and Science (Grants TIN2010-21289, TIN2010-21291-C02-02, Consolider CSD2007-00050, and Cajal Blue Brain project).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Toharia, P., Robles, O.D., Bosque, J.L. et al. Scalable shot boundary detection. J Supercomput 64, 89–99 (2013). https://doi.org/10.1007/s11227-012-0784-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-012-0784-8