Egocentric Video Biometrics

CVPR'16 Title: An Egocentric Look at Video Photographer Identity

Yedid Hoshen and Shmuel Peleg

Videos from the point of view of (a) US Marines; (b) A gun pointing robber

Abstract (2014)

Egocentric cameras are being worn by an increasing number of users, among them many security forces worldwide. GoPro cameras already penetrated the mass market, and Google Glass may follow soon. As head-worn cameras do not capture the face and body of the wearer, it may seem that the anonymity of the wearer can be preserved even when the video is publicly distributed. We show that motion features in egocentric video provide biometric information, and the identity of the user can be determined quite reliably from a few seconds of video. Biometrics are extracted by training Convolutional Neural Network (CNN) architectures on coarse optical flow.

Egocentric video biometrics can prevent theft of wearable cameras by locking the camera when worn by people other than the owner. In video sharing services, this Biometric measure can help to locate automatically all videos shot by the same user. An important message in this paper is that people should be aware that sharing egocentric video will compromise their anonymity.

arXiv Versions: Three versions can be found here.

CVPR 2016

The paper appeared in CVPR 2016, and can be downloaded here. The CVPR title was change to accommodate the reviewers. CVPR reference:

Y. Hoshen and S. Peleg, An Egocentric Look at Video Photographer Identity, CVPR'16, Las Vegas, June 2016.