Fast repetition detection in TV streams using duration patterns

Author

Carton, Ceres ; Gros, Petra

Author_Institution

Inria, Rennes, France

fYear

2013

fDate

17-19 June 2013

Firstpage

121

Lastpage

126

Abstract

This paper presents a new method to detect video repetitions in a TV stream. This method aims at reducing the number of image descriptors that have to be computed. First, shot durations are used as hash keys to propose a first set of potential repetitions. Second, a statistical test and visual descriptors are used to verify and complete these first guesses in order to improve the results by reducing the number of false detections and by retrieving the maximal length of the repeated segments. The method is tested in the context of a TV structuring application using one month of continuous TV stream.

Keywords

cryptography; image segmentation; statistical testing; television applications; video retrieval; video signal processing; video streaming; TV structuring application; continuous TV stream; duration patterns; false detections; fast video repetition detection; hash keys; image descriptors; maximal repeated segment length retrieval; shot durations; statistical test; visual descriptors; Conferences; Histograms; Image segmentation; Indexing; Streaming media; TV; Visualization;

fLanguage

English

Publisher

ieee

Conference_Titel

Content-Based Multimedia Indexing (CBMI), 2013 11th International Workshop on

Conference_Location

Veszprem

ISSN

1949-3983

Print_ISBN

978-1-4799-0955-1

Type

conf

DOI

10.1109/CBMI.2013.6576567

Filename

6576567