Interactive feature extraction and tracking by utilizing region coherency

Chris Muelder, Kwan-Liu Ma

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

27 Citations (Scopus)

Abstract

The ability to extract and follow time-varying flow features in volume data generated from large-scale numerical simulations enables scientists to effectively see and validate modeled phenomena and processes. Extracted features often take much less storage space and computing resources to visualize. Most feature extraction and tracking methods first identify features of interest in each time step independently, then correspond these features in consecutive time steps of the data. Since these methods handle each time step separately, they do not use the coherency of the feature along the time dimension in the extraction process. In this paper, we present a prediction-correction method that uses a prediction step to make the best guess of the feature region in the subsequent time step, followed by growing and shrinking the border of the predicted region to coherently extract the actual feature of interest. This method makes use of the temporal-space coherency of the data to accelerate the extraction process while implicitly solving the tedious correspondence problem that previous methods focus on. Our method is low cost with very little storage overhead, and thus facilitates interactive or runtime extraction and visualization, unlike previous methods which were largely suited for batch-mode processing due to high computational cost.

Original languageEnglish (US)
Title of host publicationIEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings
Pages17-24
Number of pages8
DOIs
StatePublished - Jul 21 2009
EventIEEE Pacific Visualization Symposium, PacificVis 2009 - Beijing, China
Duration: Apr 20 2009Apr 23 2009

Other

OtherIEEE Pacific Visualization Symposium, PacificVis 2009
CountryChina
CityBeijing
Period4/20/094/23/09

Fingerprint

Feature extraction
Costs
Visualization
Computer simulation
Processing

Keywords

  • Feature representation
  • I.4.6 [computer graphics]: Segmentation
  • Region growing, partitioning; I.4.7 [computer graphics]: Feature measurement

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Muelder, C., & Ma, K-L. (2009). Interactive feature extraction and tracking by utilizing region coherency. In IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings (pp. 17-24). [4906833] https://doi.org/10.1109/PACIFICVIS.2009.4906833

Interactive feature extraction and tracking by utilizing region coherency. / Muelder, Chris; Ma, Kwan-Liu.

IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings. 2009. p. 17-24 4906833.

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

Muelder, C & Ma, K-L 2009, Interactive feature extraction and tracking by utilizing region coherency. in IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings., 4906833, pp. 17-24, IEEE Pacific Visualization Symposium, PacificVis 2009, Beijing, China, 4/20/09. https://doi.org/10.1109/PACIFICVIS.2009.4906833
Muelder C, Ma K-L. Interactive feature extraction and tracking by utilizing region coherency. In IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings. 2009. p. 17-24. 4906833 https://doi.org/10.1109/PACIFICVIS.2009.4906833
Muelder, Chris ; Ma, Kwan-Liu. / Interactive feature extraction and tracking by utilizing region coherency. IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings. 2009. pp. 17-24
@inproceedings{805db55707574c669c8b34b56142b309,
title = "Interactive feature extraction and tracking by utilizing region coherency",
abstract = "The ability to extract and follow time-varying flow features in volume data generated from large-scale numerical simulations enables scientists to effectively see and validate modeled phenomena and processes. Extracted features often take much less storage space and computing resources to visualize. Most feature extraction and tracking methods first identify features of interest in each time step independently, then correspond these features in consecutive time steps of the data. Since these methods handle each time step separately, they do not use the coherency of the feature along the time dimension in the extraction process. In this paper, we present a prediction-correction method that uses a prediction step to make the best guess of the feature region in the subsequent time step, followed by growing and shrinking the border of the predicted region to coherently extract the actual feature of interest. This method makes use of the temporal-space coherency of the data to accelerate the extraction process while implicitly solving the tedious correspondence problem that previous methods focus on. Our method is low cost with very little storage overhead, and thus facilitates interactive or runtime extraction and visualization, unlike previous methods which were largely suited for batch-mode processing due to high computational cost.",
keywords = "Feature representation, I.4.6 [computer graphics]: Segmentation, Region growing, partitioning; I.4.7 [computer graphics]: Feature measurement",
author = "Chris Muelder and Kwan-Liu Ma",
year = "2009",
month = "7",
day = "21",
doi = "10.1109/PACIFICVIS.2009.4906833",
language = "English (US)",
isbn = "9781424444045",
pages = "17--24",
booktitle = "IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings",

}

TY - GEN

T1 - Interactive feature extraction and tracking by utilizing region coherency

AU - Muelder, Chris

AU - Ma, Kwan-Liu

PY - 2009/7/21

Y1 - 2009/7/21

N2 - The ability to extract and follow time-varying flow features in volume data generated from large-scale numerical simulations enables scientists to effectively see and validate modeled phenomena and processes. Extracted features often take much less storage space and computing resources to visualize. Most feature extraction and tracking methods first identify features of interest in each time step independently, then correspond these features in consecutive time steps of the data. Since these methods handle each time step separately, they do not use the coherency of the feature along the time dimension in the extraction process. In this paper, we present a prediction-correction method that uses a prediction step to make the best guess of the feature region in the subsequent time step, followed by growing and shrinking the border of the predicted region to coherently extract the actual feature of interest. This method makes use of the temporal-space coherency of the data to accelerate the extraction process while implicitly solving the tedious correspondence problem that previous methods focus on. Our method is low cost with very little storage overhead, and thus facilitates interactive or runtime extraction and visualization, unlike previous methods which were largely suited for batch-mode processing due to high computational cost.

AB - The ability to extract and follow time-varying flow features in volume data generated from large-scale numerical simulations enables scientists to effectively see and validate modeled phenomena and processes. Extracted features often take much less storage space and computing resources to visualize. Most feature extraction and tracking methods first identify features of interest in each time step independently, then correspond these features in consecutive time steps of the data. Since these methods handle each time step separately, they do not use the coherency of the feature along the time dimension in the extraction process. In this paper, we present a prediction-correction method that uses a prediction step to make the best guess of the feature region in the subsequent time step, followed by growing and shrinking the border of the predicted region to coherently extract the actual feature of interest. This method makes use of the temporal-space coherency of the data to accelerate the extraction process while implicitly solving the tedious correspondence problem that previous methods focus on. Our method is low cost with very little storage overhead, and thus facilitates interactive or runtime extraction and visualization, unlike previous methods which were largely suited for batch-mode processing due to high computational cost.

KW - Feature representation

KW - I.4.6 [computer graphics]: Segmentation

KW - Region growing, partitioning; I.4.7 [computer graphics]: Feature measurement

UR - http://www.scopus.com/inward/record.url?scp=67650556952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650556952&partnerID=8YFLogxK

U2 - 10.1109/PACIFICVIS.2009.4906833

DO - 10.1109/PACIFICVIS.2009.4906833

M3 - Conference contribution

SN - 9781424444045

SP - 17

EP - 24

BT - IEEE Pacific Visualization Symposium, PacificVis 2009 - Proceedings

ER -