Using control charts for on-line video summarisation

Many existing methods for video summarisation are not suitable for on-line applications, where computational and memory constraints mean that feature extraction and frame selection must be simple and efficient. Our proposed method uses RGB moments to represent frames, and a control-chart procedure t...

Full description

Saved in:
Bibliographic Details
Published inMATEC Web of Conferences Vol. 277; p. 1012
Main Authors Matthews, Clare E., Yousefi, Paria, Kuncheva, Ludmila I.
Format Journal Article Conference Proceeding
LanguageEnglish
Published Les Ulis EDP Sciences 2019
Subjects
Computer memory
Control charts
Feature extraction
Identification methods
Summaries
Online AccessGet full text

Cover

More Information
Summary:Many existing methods for video summarisation are not suitable for on-line applications, where computational and memory constraints mean that feature extraction and frame selection must be simple and efficient. Our proposed method uses RGB moments to represent frames, and a control-chart procedure to identify shots from which keyframes are then selected. The new method produces summaries of higher quality than two state-of-the-art on-line video summarisation methods identified as the best among nine such methods in our previous study. The summary quality is measured against an objective ideal for synthetic data sets, and compared to user-generated summaries of real videos.
ISSN:2261-236X
2274-7214
2261-236X
DOI:10.1051/matecconf/201927701012