Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Person re-identification by deep learning attribute-complementary information

: Schumann, A.; Stiefelhagen, R.

Postprint urn:nbn:de:0011-n-4707091 (3.4 MByte PDF)
MD5 Fingerprint: 66df675ba91351bc9b6f34042b227033
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 8.2.2018

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Proceedings : 21 - 26 July 2016, Honolulu, Hawaii
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2017
ISBN: 978-1-5386-0734-3
ISBN: 978-1-5386-0733-6
Conference on Computer Vision and Pattern Recognition Workshops (CVPR) <30, 2017, Honolulu/Hawaii>
Workshop on Target Re-Identification and Multi-Target Multi-Camera Tracking <1, 2017, Honolulu/Hawaii>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Automatic person re-identification (re-id) across camera boundaries is a challenging problem. Approaches have to be robust against many factors which influence the visual appearance of a person but are not relevant to the person's identity. Examples for such factors are pose, camera angles, and lighting conditions. Person attributes are a semantic high level information which is invariant across many such influences and contain information which is often highly relevant to a person's identity. In this work we develop a re-id approach which leverages the information contained in automatically detected attributes. We train an attribute classifier on separate data and include its responses into the training process of our person re-id model which is based on convolutional neural networks (CNNs). This allows us to learn a person representation which contains information complementary to that contained within the attributes. Our approach is able to identify attributes which perform most reliably for re-id and focus on them accordingly. We demonstrate the performance improvement gained through use of the attribute information on multiple large-scale datasets and report insights into which attributes are most relevant for person re-id.