Can I read Person Re-identification in Appearance Impaired Scenarios on EtoBox?

Person Re-identification in Appearance Impaired Scenarios by Gou, Mengran; Zhang, Xikang; Rates-Borras, Angels; Asghari-Esfeden, Sadjad; Sznaier, Mario; Camps, Octavia is a scholarly article available to read on EtoBox.

What is Person Re-identification in Appearance Impaired Scenarios about?

Person re-identification is critical in surveillance applications. Current approaches rely on appearance based features extracted from a single or multiple shots of the target and candidate matches. These approaches are at a disadvantage when trying to distinguish between candidates dressed in similar colors or when targets change their clothing. In this paper we propose a dynamics-based feature to overcome this limitation. The main idea is to capture soft biometrics from gait and motion patterns by gathering dense short trajectories (tracklets) which are Fisher vector encoded. To illustrate the merits of the proposed features we introduce three new "appearance-impaired" datasets. Our experiments on the original and the appearance impaired datasets demonstrate the benefits of incorporating dynamics-based information with appearance-based information to re-identification algorithms.

Author

Gou, Mengran; Zhang, Xikang; Rates-Borras, Angels; Asghari-Esfeden, Sadjad; Sznaier, Mario; Camps, Octavia

Published

2016

Language

EN