Abstract
Person re-identification is about recognizing people who have passed by a sensor earlier. Previous work is mainly based on RGB data, but in this work we for the first time present a system where we combine RGB, depth, and thermal data for re-identification purposes. First, from each of the three modalities, we obtain some particular features: from RGB data, we model color information from different regions of the body, from depth data, we compute different soft body biometrics, and from thermal data, we extract local structural information. Then, the three information types are combined in a joined classifier. The tri-modal system is evaluated on a new RGB-D-T dataset, showing successful results in re-identification scenarios.
Originalsprog | Engelsk |
---|---|
Titel | 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) : CVPRW 2013 |
Antal sider | 7 |
Forlag | IEEE |
Publikationsdato | 2013 |
Sider | 301-307 |
ISBN (Trykt) | 9781479909940 |
ISBN (Elektronisk) | 978-0-7695-4990-3 |
DOI | |
Status | Udgivet - 2013 |
Begivenhed | Perception Beyond the Visible Spectrum - Portland, USA Varighed: 24 jun. 2013 → 24 jun. 2013 Konferencens nummer: 9 |
Workshop
Workshop | Perception Beyond the Visible Spectrum |
---|---|
Nummer | 9 |
Land/Område | USA |
By | Portland |
Periode | 24/06/2013 → 24/06/2013 |
Fingeraftryk
Dyk ned i forskningsemnerne om 'Tri-modal Person Re-identification with RGB, Depth and Thermal Features'. Sammen danner de et unikt fingeraftryk.Forskningsdatasæt
-
AAU VAP Trimodal People Segmentation Dataset
Bahnsen, C. H. (Ophavsperson), Møgelmose, A. (Ophavsperson) & Moeslund, T. B. (Ophavsperson), Kaggle, 1 jan. 2017
DOI: 10.34740/kaggle/dsv/396257
Datasæt: Supplerende materiale