Extracting fluid from a video for efficient post-production

Makoto Okabe, Ken Anjyo, Rikio Onai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We propose a method to extract fluids from a video that is captured outside a special studio. Since such a video usually has a complex background and the fluids overlap with much transparency, it is a difficult, time-consuming task for a designer to extract them. Our goal is to develop an efficient method to solve the problem: we estimate the background of an input video, and then compute the foreground and alpha matte at each frame. Our method estimates the background by observing only pixels that have little motion at each frame. Given the estimated background, we estimate an initial alpha matte based on the color difference at every pixel between each frame and the estimated background. Since the initial alpha matte usually includes many artifacts, we employ the gradient-domain image processing approach to refine it: our method attenuates unrequired gradients adequately, and then integrate them to recover the refined alpha matte. The foreground, which explains about the color and texture pattern of the fluid itself, is also estimated in a similar manner. We demonstrate that our method enables to extract the fluids from a video, which were difficult to achieve using the previous methods.

Original languageEnglish
Title of host publicationProceedings - Digital Production Symposium 2012, DigiPro 2012
Pages53-58
Number of pages6
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventDigital Production Symposium 2012, DigiPro 2012 - Glendale, CA, United States
Duration: 2012 Aug 42012 Aug 4

Other

OtherDigital Production Symposium 2012, DigiPro 2012
CountryUnited States
CityGlendale, CA
Period12/8/412/8/4

Fingerprint

Fluids
Pixels
Color
Studios
Transparency
Image processing
Textures

Keywords

  • Alpha matte
  • Fluid
  • Post-production
  • Video processing

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Okabe, M., Anjyo, K., & Onai, R. (2012). Extracting fluid from a video for efficient post-production. In Proceedings - Digital Production Symposium 2012, DigiPro 2012 (pp. 53-58) https://doi.org/10.1145/2370919.2370928

Extracting fluid from a video for efficient post-production. / Okabe, Makoto; Anjyo, Ken; Onai, Rikio.

Proceedings - Digital Production Symposium 2012, DigiPro 2012. 2012. p. 53-58.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okabe, M, Anjyo, K & Onai, R 2012, Extracting fluid from a video for efficient post-production. in Proceedings - Digital Production Symposium 2012, DigiPro 2012. pp. 53-58, Digital Production Symposium 2012, DigiPro 2012, Glendale, CA, United States, 12/8/4. https://doi.org/10.1145/2370919.2370928
Okabe M, Anjyo K, Onai R. Extracting fluid from a video for efficient post-production. In Proceedings - Digital Production Symposium 2012, DigiPro 2012. 2012. p. 53-58 https://doi.org/10.1145/2370919.2370928
Okabe, Makoto ; Anjyo, Ken ; Onai, Rikio. / Extracting fluid from a video for efficient post-production. Proceedings - Digital Production Symposium 2012, DigiPro 2012. 2012. pp. 53-58
@inproceedings{374bb5bb05c24fc59073db4c10cda60b,
title = "Extracting fluid from a video for efficient post-production",
abstract = "We propose a method to extract fluids from a video that is captured outside a special studio. Since such a video usually has a complex background and the fluids overlap with much transparency, it is a difficult, time-consuming task for a designer to extract them. Our goal is to develop an efficient method to solve the problem: we estimate the background of an input video, and then compute the foreground and alpha matte at each frame. Our method estimates the background by observing only pixels that have little motion at each frame. Given the estimated background, we estimate an initial alpha matte based on the color difference at every pixel between each frame and the estimated background. Since the initial alpha matte usually includes many artifacts, we employ the gradient-domain image processing approach to refine it: our method attenuates unrequired gradients adequately, and then integrate them to recover the refined alpha matte. The foreground, which explains about the color and texture pattern of the fluid itself, is also estimated in a similar manner. We demonstrate that our method enables to extract the fluids from a video, which were difficult to achieve using the previous methods.",
keywords = "Alpha matte, Fluid, Post-production, Video processing",
author = "Makoto Okabe and Ken Anjyo and Rikio Onai",
year = "2012",
doi = "10.1145/2370919.2370928",
language = "English",
isbn = "9781450316491",
pages = "53--58",
booktitle = "Proceedings - Digital Production Symposium 2012, DigiPro 2012",

}

TY - GEN

T1 - Extracting fluid from a video for efficient post-production

AU - Okabe, Makoto

AU - Anjyo, Ken

AU - Onai, Rikio

PY - 2012

Y1 - 2012

N2 - We propose a method to extract fluids from a video that is captured outside a special studio. Since such a video usually has a complex background and the fluids overlap with much transparency, it is a difficult, time-consuming task for a designer to extract them. Our goal is to develop an efficient method to solve the problem: we estimate the background of an input video, and then compute the foreground and alpha matte at each frame. Our method estimates the background by observing only pixels that have little motion at each frame. Given the estimated background, we estimate an initial alpha matte based on the color difference at every pixel between each frame and the estimated background. Since the initial alpha matte usually includes many artifacts, we employ the gradient-domain image processing approach to refine it: our method attenuates unrequired gradients adequately, and then integrate them to recover the refined alpha matte. The foreground, which explains about the color and texture pattern of the fluid itself, is also estimated in a similar manner. We demonstrate that our method enables to extract the fluids from a video, which were difficult to achieve using the previous methods.

AB - We propose a method to extract fluids from a video that is captured outside a special studio. Since such a video usually has a complex background and the fluids overlap with much transparency, it is a difficult, time-consuming task for a designer to extract them. Our goal is to develop an efficient method to solve the problem: we estimate the background of an input video, and then compute the foreground and alpha matte at each frame. Our method estimates the background by observing only pixels that have little motion at each frame. Given the estimated background, we estimate an initial alpha matte based on the color difference at every pixel between each frame and the estimated background. Since the initial alpha matte usually includes many artifacts, we employ the gradient-domain image processing approach to refine it: our method attenuates unrequired gradients adequately, and then integrate them to recover the refined alpha matte. The foreground, which explains about the color and texture pattern of the fluid itself, is also estimated in a similar manner. We demonstrate that our method enables to extract the fluids from a video, which were difficult to achieve using the previous methods.

KW - Alpha matte

KW - Fluid

KW - Post-production

KW - Video processing

UR - http://www.scopus.com/inward/record.url?scp=84867379013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867379013&partnerID=8YFLogxK

U2 - 10.1145/2370919.2370928

DO - 10.1145/2370919.2370928

M3 - Conference contribution

SN - 9781450316491

SP - 53

EP - 58

BT - Proceedings - Digital Production Symposium 2012, DigiPro 2012

ER -