CINECA IRIS Institutional Research Information System
IRIS è la piattaforma adottata dall’Università degli Studi di Udine per gestire l’archivio aperto dei prodotti della ricerca. L’archivio contiene articoli, contributi in volume, monografie, interventi pubblicati in atti di convegno, Tesi di dottorato e altri materiali.
EnglishSignature-based matching has been the dominant choice for state-of-the-art person re-identification across multiple disjoint cameras. An approach that exploits image dissimilarities is proposed, treating re-identification as a binary classification problem. To achieve the objective, the person re-identification problem is addressed as follows: (i) first, compute the image dissimilarity between a pair of images acquired from two disjoint cameras; (ii) then learn the linear subspace where the image dissimilarities lie in an unsupervised fashion and (iii) lastly train a binary classifier in the linear subspace to discriminate between image dissimilarities computed for a positive pair (images are for the same person) and a negative pair (images are for different persons). An approach on two publicly available benchmark datasets is evaluated and compared with state-of-the-art methods for person re-identification. © The Institution of Engineering and Technology 2014.
| Titolo: | Person re-identification by modelling principal component analysis coefficients of image dissimilarities | |
| Autori: | ||
| Data di pubblicazione: | 2014 | |
| Rivista: | ||
| Abstract: | Signature-based matching has been the dominant choice for state-of-the-art person re-identification across multiple disjoint cameras. An approach that exploits image dissimilarities is proposed, treating re-identification as a binary classification problem. To achieve the objective, the person re-identification problem is addressed as follows: (i) first, compute the image dissimilarity between a pair of images acquired from two disjoint cameras; (ii) then learn the linear subspace where the image dissimilarities lie in an unsupervised fashion and (iii) lastly train a binary classifier in the linear subspace to discriminate between image dissimilarities computed for a positive pair (images are for the same person) and a negative pair (images are for different persons). An approach on two publicly available benchmark datasets is evaluated and compared with state-of-the-art methods for person re-identification. © The Institution of Engineering and Technology 2014. | |
| Handle: | http://hdl.handle.net/11390/1036553 | |
| Appare nelle tipologie: | 1.1 Articolo in rivista |
File in questo prodotto:
http://hdl.handle.net/11390/1036553
Copyright © 2021