An ethological motion capture system

Viktor Devecseri, A. Dóka, József Molnár, Péter Tamás

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

3 Citations (Scopus)

Abstract

The motion of living beings can be recorded with motion capture systems. The recorded data can be used to animate virtual characters. There are many methods used by motion capture systems. The paper presents the development of a motion capture system for more than one performer with active optical markers. The performers wear homogenous, illuminating markers attached to each relevant joint. Movements are captured by 6 high speed cameras in order to determine the markers' position in the cameras' image. The cameras operate at 60 fps. The image processing is distributed among multiple computers. Luckily most of the image processing tasks are highly parallel, so the high parallel computational capacity of modern programmable GPUs can be exploited. The main computer calculates the markers' 3D positions after it receives the 2D data from image processing. Each marker needs to be identified, so the markers' 2D and 3D positions are tracked. A hierarchy can be defined between the points in the point cloud, which can be used to determine the bones' hierarchical transformation chain in the characters' skeleton. To achieve satisfying results precise calibration is required.

Original languageEnglish
Title of host publication12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings
Pages487-491
Number of pages5
DOIs
Publication statusPublished - 2011
Event12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Budapest, Hungary
Duration: Nov 21 2011Nov 22 2011

Other

Other12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011
CountryHungary
CityBudapest
Period11/21/1111/22/11

Fingerprint

Image processing
Cameras
High speed cameras
Bone
Wear of materials
Calibration
Graphics processing unit

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Information Systems

Cite this

Devecseri, V., Dóka, A., Molnár, J., & Tamás, P. (2011). An ethological motion capture system. In 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings (pp. 487-491). [6108555] https://doi.org/10.1109/CINTI.2011.6108555

An ethological motion capture system. / Devecseri, Viktor; Dóka, A.; Molnár, József; Tamás, Péter.

12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings. 2011. p. 487-491 6108555.

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

Devecseri, V, Dóka, A, Molnár, J & Tamás, P 2011, An ethological motion capture system. in 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings., 6108555, pp. 487-491, 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011, Budapest, Hungary, 11/21/11. https://doi.org/10.1109/CINTI.2011.6108555
Devecseri V, Dóka A, Molnár J, Tamás P. An ethological motion capture system. In 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings. 2011. p. 487-491. 6108555 https://doi.org/10.1109/CINTI.2011.6108555
Devecseri, Viktor ; Dóka, A. ; Molnár, József ; Tamás, Péter. / An ethological motion capture system. 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings. 2011. pp. 487-491
@inproceedings{9cfabc4e12b94bf9886aa9b8f0a45fa8,
title = "An ethological motion capture system",
abstract = "The motion of living beings can be recorded with motion capture systems. The recorded data can be used to animate virtual characters. There are many methods used by motion capture systems. The paper presents the development of a motion capture system for more than one performer with active optical markers. The performers wear homogenous, illuminating markers attached to each relevant joint. Movements are captured by 6 high speed cameras in order to determine the markers' position in the cameras' image. The cameras operate at 60 fps. The image processing is distributed among multiple computers. Luckily most of the image processing tasks are highly parallel, so the high parallel computational capacity of modern programmable GPUs can be exploited. The main computer calculates the markers' 3D positions after it receives the 2D data from image processing. Each marker needs to be identified, so the markers' 2D and 3D positions are tracked. A hierarchy can be defined between the points in the point cloud, which can be used to determine the bones' hierarchical transformation chain in the characters' skeleton. To achieve satisfying results precise calibration is required.",
author = "Viktor Devecseri and A. D{\'o}ka and J{\'o}zsef Moln{\'a}r and P{\'e}ter Tam{\'a}s",
year = "2011",
doi = "10.1109/CINTI.2011.6108555",
language = "English",
isbn = "9781457700453",
pages = "487--491",
booktitle = "12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings",

}

TY - GEN

T1 - An ethological motion capture system

AU - Devecseri, Viktor

AU - Dóka, A.

AU - Molnár, József

AU - Tamás, Péter

PY - 2011

Y1 - 2011

N2 - The motion of living beings can be recorded with motion capture systems. The recorded data can be used to animate virtual characters. There are many methods used by motion capture systems. The paper presents the development of a motion capture system for more than one performer with active optical markers. The performers wear homogenous, illuminating markers attached to each relevant joint. Movements are captured by 6 high speed cameras in order to determine the markers' position in the cameras' image. The cameras operate at 60 fps. The image processing is distributed among multiple computers. Luckily most of the image processing tasks are highly parallel, so the high parallel computational capacity of modern programmable GPUs can be exploited. The main computer calculates the markers' 3D positions after it receives the 2D data from image processing. Each marker needs to be identified, so the markers' 2D and 3D positions are tracked. A hierarchy can be defined between the points in the point cloud, which can be used to determine the bones' hierarchical transformation chain in the characters' skeleton. To achieve satisfying results precise calibration is required.

AB - The motion of living beings can be recorded with motion capture systems. The recorded data can be used to animate virtual characters. There are many methods used by motion capture systems. The paper presents the development of a motion capture system for more than one performer with active optical markers. The performers wear homogenous, illuminating markers attached to each relevant joint. Movements are captured by 6 high speed cameras in order to determine the markers' position in the cameras' image. The cameras operate at 60 fps. The image processing is distributed among multiple computers. Luckily most of the image processing tasks are highly parallel, so the high parallel computational capacity of modern programmable GPUs can be exploited. The main computer calculates the markers' 3D positions after it receives the 2D data from image processing. Each marker needs to be identified, so the markers' 2D and 3D positions are tracked. A hierarchy can be defined between the points in the point cloud, which can be used to determine the bones' hierarchical transformation chain in the characters' skeleton. To achieve satisfying results precise calibration is required.

UR - http://www.scopus.com/inward/record.url?scp=84855928941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855928941&partnerID=8YFLogxK

U2 - 10.1109/CINTI.2011.6108555

DO - 10.1109/CINTI.2011.6108555

M3 - Conference contribution

SN - 9781457700453

SP - 487

EP - 491

BT - 12th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2011 - Proceedings

ER -