Open Access

Identification of video subsequence using bipartite graph matching

  • Silvio Jamil Ferzoli Guimarães1Email author and
  • Zenilton Kleber Gonçalves do PatrocínioJr.1
Journal of the Brazilian Computer Society201117:36

https://doi.org/10.1007/s13173-011-0036-4

Received: 16 February 2011

Accepted: 13 July 2011

Published: 7 September 2011

Abstract

Subsequence identification consists of identifying real positions of a specific video clip in a video stream together with the operations that may be used to transform the former into a subsequence from the latter. To cope with this problem, we propose a new approach, considering a bipartite graph matching to measure video clip similarity with a target video stream which has not been preprocessed.

The main contributions of our work are the application of a simple and efficient distance to solve the subsequence identification problem along with the definition of a hit function that identifies precisely which operations were used in query transformation. Experimental results demonstrate that our method performances achieve 90% recall with 93% precision, though it is done without preprocessing of the target video.

Keywords

Video retrieval Graph bipartite Video clip localization

Notes