Communication-efficient multi-view keyframe extraction in distributed video sensors

Shun Hsing Ou, Yu Chen Lu, Jui Pin Wang, Shao Yi Chien, Shou De Lin, Mi Yen Yeti, Chia Han Lee, Phillip B. Gibbons, V. Srinivasa Somayazulu, Yen Kuang Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Video sensors are widely used in many applications such as security monitoring and home care. However, the growth of the number of sensors makes it impractical to stream all videos back to a central server for further processing, due to communication bandwidth and server storage constraints. Multi-view video summarization allows us to discard redundant data in the video streams taken by a group of sensors. All prior multi-view summarization methods, however, process video data in an off-line and centralized manner, which means that all videos are still required to be streamed back to the server before conducting the summarization. This paper proposes an on-line, distributed multi-view summarization system, which integrates the ideas of Maximal Marginal Relevance (MMR) and MS-Wave, a bandwidth-efficient distributed algorithm for finding k-nearest-neighbors and k-farthest-neighbors. Empirical studies show that our proposed system can discard redundant videos and keep important keyframes as effectively as centralized approaches, while transmitting only 1/6 to 1/3 as much data.

Original languageEnglish
Title of host publication2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages13-16
Number of pages4
ISBN (Electronic)9781479961399
DOIs
StatePublished - 27 Feb 2015
Event2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014 - Valletta, Malta
Duration: 7 Dec 201410 Dec 2014

Publication series

Name2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014

Conference

Conference2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014
CountryMalta
CityValletta
Period7/12/1410/12/14

Fingerprint Dive into the research topics of 'Communication-efficient multi-view keyframe extraction in distributed video sensors'. Together they form a unique fingerprint.

  • Cite this

    Ou, S. H., Lu, Y. C., Wang, J. P., Chien, S. Y., Lin, S. D., Yeti, M. Y., Lee, C. H., Gibbons, P. B., Somayazulu, V. S., & Chen, Y. K. (2015). Communication-efficient multi-view keyframe extraction in distributed video sensors. In 2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014 (pp. 13-16). [7051492] (2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VCIP.2014.7051492