Features accumulation on a multiple view oriented model for people re-identification

Authors:
J. García;A. Gardel;I. Bravo;J. L. Lázaro;C. Kambhamettu
Affiliations:
University of Alcalá, Alcalá de Henares, Madrid, Spain;University of Alcalá, Alcalá de Henares, Madrid, Spain;University of Alcalá, Alcalá de Henares, Madrid, Spain;University of Alcalá, Alcalá de Henares, Madrid, Spain;University of Delaware, Newark, DE
Venue:
3DOR '13 Proceedings of the Sixth Eurographics Workshop on 3D Object Retrieval
Year:
2013

Citing 7
Cited 0

Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
People Reidentification in a Camera Network

DASC '09 Proceedings of the 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing
Person Re-identification Using Haar-based and DCD-based Signature

AVSS '10 Proceedings of the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance
Evaluation of local features for person re-identification in image sequences

AVSS '11 Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance
Multiple-shot human re-identification by Mean Riemannian Covariance Grid

AVSS '11 Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance
Relaxed pairwise learned metric for person re-identification

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Reidentification by Relative Distance Comparison

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

People re-identification process provides relevant information in order to understand the scene. In this paper, we present a multiple-view oriented model for performing people re-identification in a camera network. An appearance model for different perspectives is generated from people trajectories. Global and local features besides path orientation are extracted from each person's image, given a short-term tracking. Experimental results based on different sets of features demonstrate the effectiveness of our system.