On deeply learning features for automatic person re-identification

Alexandre Franco

ISBN 10: 3330029102 / ISBN 13: 9783330029101

Edité par LAP LAMBERT Academic Publishing, 2017

A propos de cet article

nach der Bestellung gedruckt Neuware - Printed after ordering - The automatic person re-identification problem resides in matching an unknown person image to a database of previously labeled images of people. Comparison among two image features is commonly accomplished by distance metrics. Although features and distance metrics can be handcrafted or trainable, the latter type has demonstrated more potential to breakthroughs in achieving state-of-the-art performance over public data sets. A recent paradigm that allows to work with trainable features is deep learning. In this book, we present a novel deep learning strategy, so called coarse-to-fine learning (CFL), as well as a novel type of feature - the convolutional covariance features (CCF), for person re-identification. CFL is based on the human learning process. After extracting the convolutional features via CFL, those ones are then wrapped in covariance matrices, composing the CCF. The performance of the proposed framework was assessed comparatively against 18 state-of-the-art methods by using public data sets (VIPeR, i-LIDS, CUHK01 and CUHK03), achieving superior performance.

N° de réf. du vendeur 9783330029101

Détails bibliographiques

• Titre: On deeply learning features for automatic person re-identification
• Éditeur: LAP LAMBERT Academic Publishing
• Date de parution: 2017
• Langue: anglais
• ISBN à 10 chiffres: 3330029102
• ISBN à 13 chiffres: 9783330029101
• Reliure: Taschenbuch
• État de l'article: Neu
• Dimensions: 220 L x 150 H x 7 P (en millimètres) 220 millimètres de largeur par 150 millimètres de hauteur par 7 millimètres de profondeur
• Poids: 185 grammes

A propos de ce titre

Synopsis

The automatic person re-identification problem resides in matching an unknown person image to a database of previously labeled images of people. Comparison among two image features is commonly accomplished by distance metrics. Although features and distance metrics can be handcrafted or trainable, the latter type has demonstrated more potential to breakthroughs in achieving state-of-the-art performance over public data sets. A recent paradigm that allows to work with trainable features is deep learning. In this book, we present a novel deep learning strategy, so called coarse-to-fine learning (CFL), as well as a novel type of feature - the convolutional covariance features (CCF), for person re-identification. CFL is based on the human learning process. After extracting the convolutional features via CFL, those ones are then wrapped in covariance matrices, composing the CCF. The performance of the proposed framework was assessed comparatively against 18 state-of-the-art methods by using public data sets (VIPeR, i-LIDS, CUHK01 and CUHK03), achieving superior performance.