EgoSampling: Fast-forward and stereo for egocentric videos

Yair Poleg; Tavi Halperin; Chetan Arora; Shmuel Peleg

doi:10.1109/CVPR.2015.7299109

EgoSampling: Fast-forward and stereo for egocentric videos

Yair Poleg, Tavi Halperin, Chetan Arora, Shmuel Peleg

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

52 Scopus citations

Abstract

While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	4768-4776
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299109
State	Published - 14 Oct 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Access to Document

10.1109/CVPR.2015.7299109

Cite this

Poleg, Y., Halperin, T., Arora, C., & Peleg, S. (2015). EgoSampling: Fast-forward and stereo for egocentric videos. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 4768-4776). Article 7299109 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299109

@inproceedings{f1c515536cc0483395011d68547f37d4,

title = "EgoSampling: Fast-forward and stereo for egocentric videos",

abstract = "While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.",

author = "Yair Poleg and Tavi Halperin and Chetan Arora and Shmuel Peleg",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7299109",

language = "אנגלית",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "4768--4776",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

address = "ארצות הברית",

}

Poleg, Y, Halperin, T, Arora, C & Peleg, S 2015, EgoSampling: Fast-forward and stereo for egocentric videos. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299109, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 4768-4776, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPR.2015.7299109

EgoSampling: Fast-forward and stereo for egocentric videos. / Poleg, Yair; Halperin, Tavi; Arora, Chetan et al.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 4768-4776 7299109 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - EgoSampling

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

AU - Poleg, Yair

AU - Halperin, Tavi

AU - Arora, Chetan

AU - Peleg, Shmuel

PY - 2015/10/14

Y1 - 2015/10/14

N2 - While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.

AB - While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.

UR - http://www.scopus.com/inward/record.url?scp=84959193371&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299109

DO - 10.1109/CVPR.2015.7299109

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84959193371

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 4768

EP - 4776

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

Y2 - 7 June 2015 through 12 June 2015

ER -

EgoSampling: Fast-forward and stereo for egocentric videos

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this