Proceedings of the First ACM International Conference on Multimedia - MULTIMEDIA '93 1993
DOI: 10.1145/166266.166295
|View full text |Cite
|
Sign up to set email alerts
|

Projection detecting filter for video cut detection

Abstract: Abstract. This paper discusses a video cut detection method. Cut detection is an important technique for making videos easier to handle. First, this paper analyzes the distribution of the image difference V to clarify the characteristics that make V suitable for cut detection. We propose a cut detection method that uses a projection (an isolated sharp peak) detecting filter. A motion sensitive V is used to stabilize V projections at cuts, and cuts are detected more reliably with this filter. The method can ach… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

1996
1996
2003
2003

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 65 publications
(19 citation statements)
references
References 2 publications
0
19
0
Order By: Relevance
“…The last feature used is linked to spatio-temporal volumes. These volumes are built thanks to the projection of the video data along the (x, t) and the (y, t) planes, as in [67]. For a given sequence, edges perpendicular to the t axis may indicate shot changes.…”
Section: Combination Of Several Methodsmentioning
confidence: 99%
“…The last feature used is linked to spatio-temporal volumes. These volumes are built thanks to the projection of the video data along the (x, t) and the (y, t) planes, as in [67]. For a given sequence, edges perpendicular to the t axis may indicate shot changes.…”
Section: Combination Of Several Methodsmentioning
confidence: 99%
“…That is, such semantic contents themselves are not extracted from video data, but the editorial technique is extracted to evaluate the semantic contents. Prior to the extraction of scene features, the process of cut detection [37] or extraction of scene unit [48] is mandatory for automated parsing of video data.…”
Section: Cbr By Derivation Knowledgementioning
confidence: 99%
“…Existing work has relied directly on intensity data, using such t e c hniques as image di erencing and intensity histogramming. Most approaches are based on intensity histograms, and concentrate on cuts 6,7] These methods have di culty with \busy" scenes, in which i n tensities change substantially from frame to frame. Such c hanges often result from camera or object motion.…”
Section: Scene Break Detectionmentioning
confidence: 99%