Home > Research > Publications & Outputs > Spatio-temporal motion tracking with unsynchron...
View graph of relations

Spatio-temporal motion tracking with unsynchronized cameras

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Spatio-temporal motion tracking with unsynchronized cameras. / Elhayek, A.; Stoll, C.; Hasler, N.; Kim, K. I.; Seidel, H.-P.; Theobalt, C.

Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2012. p. 1870-1877.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Elhayek, A, Stoll, C, Hasler, N, Kim, KI, Seidel, H-P & Theobalt, C 2012, Spatio-temporal motion tracking with unsynchronized cameras. in Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 1870-1877. https://doi.org/10.1109/CVPR.2012.6247886

APA

Elhayek, A., Stoll, C., Hasler, N., Kim, K. I., Seidel, H-P., & Theobalt, C. (2012). Spatio-temporal motion tracking with unsynchronized cameras. In Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1870-1877). IEEE. https://doi.org/10.1109/CVPR.2012.6247886

Vancouver

Elhayek A, Stoll C, Hasler N, Kim KI, Seidel H-P, Theobalt C. Spatio-temporal motion tracking with unsynchronized cameras. In Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. 2012. p. 1870-1877 https://doi.org/10.1109/CVPR.2012.6247886

Author

Elhayek, A. ; Stoll, C. ; Hasler, N. ; Kim, K. I. ; Seidel, H.-P. ; Theobalt, C. / Spatio-temporal motion tracking with unsynchronized cameras. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2012. pp. 1870-1877

Bibtex

@inproceedings{6db27ed2e38f40e3a029efcfc9db911a,
title = "Spatio-temporal motion tracking with unsynchronized cameras",
abstract = "We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cameras to be synchronized and without aligning captured frames in time. By formulating the model-to-image similarity measure as a temporally continuous functional, we are also able to reconstruct motion in much higher temporal detail than was possible with previous synchronized approaches. By purposefully running cameras unsynchronized we can capture even very fast motion at speeds that off-the-shelf but high quality cameras provide.",
keywords = "cameras, image motion analysis, image reconstruction, image sequences, object tracking, pose estimation, video signal processing, character motion reconstruction, character pose reconstruction, markerless motion capture, model-to-image similarity measure, multiview video sequence, spatio-temporal motion tracking, unsynchronized cameras, Cameras, Image color analysis, Joints, Motion segmentation, Streaming media, Synchronization, Tracking",
author = "A. Elhayek and C. Stoll and N. Hasler and Kim, {K. I.} and H.-P. Seidel and C. Theobalt",
year = "2012",
doi = "10.1109/CVPR.2012.6247886",
language = "English",
isbn = "9781467312264",
pages = "1870--1877",
booktitle = "Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Spatio-temporal motion tracking with unsynchronized cameras

AU - Elhayek, A.

AU - Stoll, C.

AU - Hasler, N.

AU - Kim, K. I.

AU - Seidel, H.-P.

AU - Theobalt, C.

PY - 2012

Y1 - 2012

N2 - We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cameras to be synchronized and without aligning captured frames in time. By formulating the model-to-image similarity measure as a temporally continuous functional, we are also able to reconstruct motion in much higher temporal detail than was possible with previous synchronized approaches. By purposefully running cameras unsynchronized we can capture even very fast motion at speeds that off-the-shelf but high quality cameras provide.

AB - We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cameras to be synchronized and without aligning captured frames in time. By formulating the model-to-image similarity measure as a temporally continuous functional, we are also able to reconstruct motion in much higher temporal detail than was possible with previous synchronized approaches. By purposefully running cameras unsynchronized we can capture even very fast motion at speeds that off-the-shelf but high quality cameras provide.

KW - cameras

KW - image motion analysis

KW - image reconstruction

KW - image sequences

KW - object tracking

KW - pose estimation

KW - video signal processing

KW - character motion reconstruction

KW - character pose reconstruction

KW - markerless motion capture

KW - model-to-image similarity measure

KW - multiview video sequence

KW - spatio-temporal motion tracking

KW - unsynchronized cameras

KW - Cameras

KW - Image color analysis

KW - Joints

KW - Motion segmentation

KW - Streaming media

KW - Synchronization

KW - Tracking

U2 - 10.1109/CVPR.2012.6247886

DO - 10.1109/CVPR.2012.6247886

M3 - Conference contribution/Paper

SN - 9781467312264

SP - 1870

EP - 1877

BT - Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PB - IEEE

ER -