Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors

Suk Ho Lee, Moon Gi Kang

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

Abstract

In this paper, we propose a new representation of the location of the target that aims for the application of object tracking with non-stationary cameras and non-rigid motion: the area weighted mean of the centroids corresponding to each color bin of the target. With this representation, the target localization in the next frame can be achieved by a direct one step computation. The tracking based on this representation has several advantages such as being possible to track in low-rate-frame environment, allowing partial occlusion and being fast due to the one step computation. We also propose a background feature elimination algorithm which is based on the level set based bimodal segmentation and is incorporated into the tracking scheme to increase the robustness of the scheme.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008
DOIs
Publication statusPublished - 2008 May 21
EventVisual Communications and Image Processing 2008 - San Jose, CA, United States
Duration: 2008 Jan 292008 Jan 31

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6822
ISSN (Print)0277-786X

Other

OtherVisual Communications and Image Processing 2008
CountryUnited States
CitySan Jose, CA
Period08/1/2908/1/31

Fingerprint

Motion Tracking
Weighted Average
Centroid
Level Set
centroids
Camera
Cameras
cameras
Target
Bins
Weighted Mean
occlusion
Object Tracking
Bimodal
Color
Occlusion
Elimination
elimination
Segmentation
Robustness

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Lee, S. H., & Kang, M. G. (2008). Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors. In Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008 [682209] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6822). https://doi.org/10.1117/12.765724
Lee, Suk Ho ; Kang, Moon Gi. / Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors. Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008. 2008. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{771189af4d8d425d821b9685180febb8,
title = "Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors",
abstract = "In this paper, we propose a new representation of the location of the target that aims for the application of object tracking with non-stationary cameras and non-rigid motion: the area weighted mean of the centroids corresponding to each color bin of the target. With this representation, the target localization in the next frame can be achieved by a direct one step computation. The tracking based on this representation has several advantages such as being possible to track in low-rate-frame environment, allowing partial occlusion and being fast due to the one step computation. We also propose a background feature elimination algorithm which is based on the level set based bimodal segmentation and is incorporated into the tracking scheme to increase the robustness of the scheme.",
author = "Lee, {Suk Ho} and Kang, {Moon Gi}",
year = "2008",
month = "5",
day = "21",
doi = "10.1117/12.765724",
language = "English",
isbn = "9780819469946",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008",

}

Lee, SH & Kang, MG 2008, Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors. in Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008., 682209, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6822, Visual Communications and Image Processing 2008, San Jose, CA, United States, 08/1/29. https://doi.org/10.1117/12.765724

Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors. / Lee, Suk Ho; Kang, Moon Gi.

Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008. 2008. 682209 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6822).

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

TY - GEN

T1 - Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors

AU - Lee, Suk Ho

AU - Kang, Moon Gi

PY - 2008/5/21

Y1 - 2008/5/21

N2 - In this paper, we propose a new representation of the location of the target that aims for the application of object tracking with non-stationary cameras and non-rigid motion: the area weighted mean of the centroids corresponding to each color bin of the target. With this representation, the target localization in the next frame can be achieved by a direct one step computation. The tracking based on this representation has several advantages such as being possible to track in low-rate-frame environment, allowing partial occlusion and being fast due to the one step computation. We also propose a background feature elimination algorithm which is based on the level set based bimodal segmentation and is incorporated into the tracking scheme to increase the robustness of the scheme.

AB - In this paper, we propose a new representation of the location of the target that aims for the application of object tracking with non-stationary cameras and non-rigid motion: the area weighted mean of the centroids corresponding to each color bin of the target. With this representation, the target localization in the next frame can be achieved by a direct one step computation. The tracking based on this representation has several advantages such as being possible to track in low-rate-frame environment, allowing partial occlusion and being fast due to the one step computation. We also propose a background feature elimination algorithm which is based on the level set based bimodal segmentation and is incorporated into the tracking scheme to increase the robustness of the scheme.

UR - http://www.scopus.com/inward/record.url?scp=43649087710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43649087710&partnerID=8YFLogxK

U2 - 10.1117/12.765724

DO - 10.1117/12.765724

M3 - Conference contribution

AN - SCOPUS:43649087710

SN - 9780819469946

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008

ER -

Lee SH, Kang MG. Motion tracking with non-stationary camera based on area and level set weighted average of centroid shifting vectors. In Proceedings of SPIE-IS and T Electronic Imaging - Visual Communications and Image Processing 2008. 2008. 682209. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.765724