Content-Based Retrieval of Compressed Videos

  • Jurandy Almeida UNICAMP
  • Neucimar J. Leite UNICAMP
  • Ricardo da S. Torres UNICAMP

Abstract


Most of existing systems for video retrieval rely on algorithms and methods which are computationally expensive, limiting their scope of application. Contrary to this trend, the market has shown a growing demand for mobile and embedded devices. In this context, this thesis introduces five novel approaches for the analysis, indexing, and retrieval of digital videos in limited capacity devices. All these contributions are combined to create a computationally fast system, which is able to achieve a quality level superior to current solutions.

References

Almeida, J. (2011). Recuperação de Vídeos Comprimidos por Conteúdo. PhD thesis, Instituto de Computação, Unicamp, Campinas, SP, Brazil.

Almeida, J., Leite, N. J., and Torres, R. S. (2011a). Comparison of video sequences with histograms of motion patterns. In IEEE Int. Conf. Image Process. (ICIP’11), pages 3673–3676.

Almeida, J., Leite, N. J., and Torres, R. S. (2011b). Rapid cut detection on compressed video. In Iberoamerican Congress Pattern Recog. (CIARP’11), pages 71–78.

Almeida, J., Leite, N. J., and Torres, R. S. (2012a). Online video summarization on compressed domain. J. Visual Communication and Image Representation (JVCIR). DOI: 10.1016/j.jvcir.2012.01.009.

Almeida, J., Leite, N. J., and Torres, R. S. (2012b). VISON: VIdeo Summarization for ONline applications. Pattern Recog. Letters (PRL), 33(4):397–409.

Almeida, J., Minetto, R., Almeida, T. A., Torres, R. S., and Leite, N. J. (2009). Robust estimation of camera motion using optical flow models. In Int. Symp. Visual Computing (ISVC’09), pages 435–446.

Almeida, J., Minetto, R., Almeida, T. A., Torres, R. S., and Leite, N. J. (2010a). Estimation of camera parameters in video sequences with a large amount of scene motion. In Int. Work. Systems, Signals and Image Process. (IWSSIP’10), pages 348–351.

Almeida, J., Torres, R. S., and Leite, N. J. (2010b). BP-tree: An efficient index for similarity search in high-dimensional metric spaces. In ACM Int. Conf. Inf. Knowl. Management (CIKM’10), pages 1365–1368.

Almeida, J., Torres, R. S., and Leite, N. J. (2010c). Rapid video summarization on compressed video. In IEEE Int. Symp. Multimedia (ISM’10), pages 113–120.

Almeida, J., Valle, E., Torres, R. S., and Leite, N. J. (2010d). DAHC-tree: An effective index for approximate search in high-dimensional metric spaces. J. Information and Data Management (JIDM), 1(3):375–390.

Kozievitch, N. P., Almeida, J., Torres, R. S., Leite, N. J., Gonçalves, M. A., Murthy, U., and Fox, E. A. (2011a). Towards a formal theory for complex objects and content-based image retrieval. J. Information and Data Management (JIDM), 2(3):321–336.

Kozievitch, N. P., Almeida, J., Torres, R. S., Santanchè, A., and Leite, N. J. (2011b). Reusing a compound-based infrastructure for searching video stories. In IEEE Int. Conf. Inf. Reuse Integration (IRI’11), pages 222–227.

Li, L. T., Almeida, J., and Torres, R. S. (2011). RECOD working notes for placing task mediaeval 2011. In Working Notes Proceedings of the MediaEval 2011 Workshop (MEDIAEVAL’11).

Pinto-Cáceres, S. M., Almeida, J., Neris, V. P. A., Baranauskas, M. C. C., Leite, N. J., and Torres, R. S. (2011). Navigating through video stories using clustering sets. Int. J. Multimedia Data Eng. Management (IJMDEM), 2(3):1–20.
Published
2012-07-16
ALMEIDA, Jurandy; LEITE, Neucimar J.; TORRES, Ricardo da S.. Content-Based Retrieval of Compressed Videos. In: THESIS AND DISSERTATION CONTEST (CTD), 15. , 2012, Curitiba/PR. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2012 . p. 25-30. ISSN 2763-8820.