A Mid-level Description of Video, with Application to Non-photorealistic Animation

J P Collomosse, P M Hall

Research output: Contribution to conferencePaper

Abstract

The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying database which describes objects in the video. We explain how to automatically process video into our description, and use it to solve a long-standing problem in Computer Graphics; that of automatically producing non-photorealistic (NPR) animations from video sequences. We show empirically that our description is highly compact relative to alternative coding schemes, and that our NPR animation technique out performs the current state-of-the-art in automatic video painting by about an order of magnitude, in terms of temporal coherence.
LanguageEnglish
Pages7--16
Number of pages10
StatusPublished - Sep 2004
Event15th British Machine Vision Conference (BMVC) -
Duration: 1 Sep 2004 → …

Conference

Conference15th British Machine Vision Conference (BMVC)
Period1/09/04 → …

Fingerprint

Animation
Painting
Computer graphics

Cite this

Collomosse, J. P., & Hall, P. M. (2004). A Mid-level Description of Video, with Application to Non-photorealistic Animation. 7--16. Paper presented at 15th British Machine Vision Conference (BMVC), .

A Mid-level Description of Video, with Application to Non-photorealistic Animation. / Collomosse, J P; Hall, P M.

2004. 7--16 Paper presented at 15th British Machine Vision Conference (BMVC), .

Research output: Contribution to conferencePaper

Collomosse, JP & Hall, PM 2004, 'A Mid-level Description of Video, with Application to Non-photorealistic Animation' Paper presented at 15th British Machine Vision Conference (BMVC), 1/09/04, pp. 7--16.
Collomosse JP, Hall PM. A Mid-level Description of Video, with Application to Non-photorealistic Animation. 2004. Paper presented at 15th British Machine Vision Conference (BMVC), .
Collomosse, J P ; Hall, P M. / A Mid-level Description of Video, with Application to Non-photorealistic Animation. Paper presented at 15th British Machine Vision Conference (BMVC), .10 p.
@conference{50e1cc60c57f40a9979c85e69ff298e2,
title = "A Mid-level Description of Video, with Application to Non-photorealistic Animation",
abstract = "The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying database which describes objects in the video. We explain how to automatically process video into our description, and use it to solve a long-standing problem in Computer Graphics; that of automatically producing non-photorealistic (NPR) animations from video sequences. We show empirically that our description is highly compact relative to alternative coding schemes, and that our NPR animation technique out performs the current state-of-the-art in automatic video painting by about an order of magnitude, in terms of temporal coherence.",
author = "Collomosse, {J P} and Hall, {P M}",
year = "2004",
month = "9",
language = "English",
pages = "7----16",
note = "15th British Machine Vision Conference (BMVC) ; Conference date: 01-09-2004",

}

TY - CONF

T1 - A Mid-level Description of Video, with Application to Non-photorealistic Animation

AU - Collomosse, J P

AU - Hall, P M

PY - 2004/9

Y1 - 2004/9

N2 - The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying database which describes objects in the video. We explain how to automatically process video into our description, and use it to solve a long-standing problem in Computer Graphics; that of automatically producing non-photorealistic (NPR) animations from video sequences. We show empirically that our description is highly compact relative to alternative coding schemes, and that our NPR animation technique out performs the current state-of-the-art in automatic video painting by about an order of magnitude, in terms of temporal coherence.

AB - The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying database which describes objects in the video. We explain how to automatically process video into our description, and use it to solve a long-standing problem in Computer Graphics; that of automatically producing non-photorealistic (NPR) animations from video sequences. We show empirically that our description is highly compact relative to alternative coding schemes, and that our NPR animation technique out performs the current state-of-the-art in automatic video painting by about an order of magnitude, in terms of temporal coherence.

M3 - Paper

SP - 7

EP - 16

ER -