Standard
Feature-based multi-video synchronization with subframe accuracy. / Elhayek, Ahmed; Stoll, Carsten
; Kim, Kwang In et al.
Pattern recognition: Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012. Proceedings. ed. / Axel Pinz; Thomas Pock; Horst Bischof; Franz Liberl. Berlin: Springer Verlag, 2012. p. 266-275 (Lecture Notes in Computer Science; Vol. 7476).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Elhayek, A, Stoll, C
, Kim, KI, Seidel, H-P & Theobalt, C 2012,
Feature-based multi-video synchronization with subframe accuracy. in A Pinz, T Pock, H Bischof & F Liberl (eds),
Pattern recognition: Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012. Proceedings. Lecture Notes in Computer Science, vol. 7476, Springer Verlag, Berlin, pp. 266-275.
https://doi.org/10.1007/978-3-642-32717-9_27
APA
Elhayek, A., Stoll, C.
, Kim, K. I., Seidel, H.-P., & Theobalt, C. (2012).
Feature-based multi-video synchronization with subframe accuracy. In A. Pinz, T. Pock, H. Bischof, & F. Liberl (Eds.),
Pattern recognition: Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012. Proceedings (pp. 266-275). (Lecture Notes in Computer Science; Vol. 7476). Springer Verlag.
https://doi.org/10.1007/978-3-642-32717-9_27
Vancouver
Elhayek A, Stoll C
, Kim KI, Seidel HP, Theobalt C.
Feature-based multi-video synchronization with subframe accuracy. In Pinz A, Pock T, Bischof H, Liberl F, editors, Pattern recognition: Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012. Proceedings. Berlin: Springer Verlag. 2012. p. 266-275. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-32717-9_27
Author
Bibtex
@inproceedings{19d0b1107493496e90c50e8c26a15b26,
title = "Feature-based multi-video synchronization with subframe accuracy",
abstract = "We present a novel algorithm for temporally synchronizing multiple videos capturing the same dynamic scene. Our algorithm relies on general image features and it does not require explicitly tracking any specific object, making it applicable to general scenes with complex motion. This is facilitated by our new trajectory filtering and matching schemes that correctly identifies matching pairs of trajectories (inliers) from a large set of potential candidate matches, of which many are outliers. We find globally optimal synchronization parameters by using a stable RANSAC-based optimization approach. For multi-video synchronization, the algorithm identifies an informative subset of video pairs which prevents the RANSAC algorithm from being biased by outliers. Experiments on two-camera and multi-camera synchronization demonstrate the performance of our algorithm.",
author = "Ahmed Elhayek and Carsten Stoll and Kim, {Kwang In} and Hans-Peter Seidel and Christian Theobalt",
year = "2012",
doi = "10.1007/978-3-642-32717-9_27",
language = "English",
isbn = "9783642327162",
series = "Lecture Notes in Computer Science",
publisher = "Springer Verlag",
pages = "266--275",
editor = "Axel Pinz and Thomas Pock and Horst Bischof and Franz Liberl",
booktitle = "Pattern recognition",
}
RIS
TY - GEN
T1 - Feature-based multi-video synchronization with subframe accuracy
AU - Elhayek, Ahmed
AU - Stoll, Carsten
AU - Kim, Kwang In
AU - Seidel, Hans-Peter
AU - Theobalt, Christian
PY - 2012
Y1 - 2012
N2 - We present a novel algorithm for temporally synchronizing multiple videos capturing the same dynamic scene. Our algorithm relies on general image features and it does not require explicitly tracking any specific object, making it applicable to general scenes with complex motion. This is facilitated by our new trajectory filtering and matching schemes that correctly identifies matching pairs of trajectories (inliers) from a large set of potential candidate matches, of which many are outliers. We find globally optimal synchronization parameters by using a stable RANSAC-based optimization approach. For multi-video synchronization, the algorithm identifies an informative subset of video pairs which prevents the RANSAC algorithm from being biased by outliers. Experiments on two-camera and multi-camera synchronization demonstrate the performance of our algorithm.
AB - We present a novel algorithm for temporally synchronizing multiple videos capturing the same dynamic scene. Our algorithm relies on general image features and it does not require explicitly tracking any specific object, making it applicable to general scenes with complex motion. This is facilitated by our new trajectory filtering and matching schemes that correctly identifies matching pairs of trajectories (inliers) from a large set of potential candidate matches, of which many are outliers. We find globally optimal synchronization parameters by using a stable RANSAC-based optimization approach. For multi-video synchronization, the algorithm identifies an informative subset of video pairs which prevents the RANSAC algorithm from being biased by outliers. Experiments on two-camera and multi-camera synchronization demonstrate the performance of our algorithm.
U2 - 10.1007/978-3-642-32717-9_27
DO - 10.1007/978-3-642-32717-9_27
M3 - Conference contribution/Paper
SN - 9783642327162
T3 - Lecture Notes in Computer Science
SP - 266
EP - 275
BT - Pattern recognition
A2 - Pinz, Axel
A2 - Pock, Thomas
A2 - Bischof, Horst
A2 - Liberl, Franz
PB - Springer Verlag
CY - Berlin
ER -