Person re-identification by modelling principal component analysis coefficients of image dissimilarities

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-id...

Full description

Saved in:
Bibliographic Details
Published in:Electronics letters Vol. 50; no. 14; pp. 1000 - 1001
Main Authors: Martinel, N, Micheloni, C
Format: Journal Article
Language:English
Published: Stevenage The Institution of Engineering and Technology 03.07.2014
Institution of Engineering and Technology
John Wiley & Sons, Inc
Subjects:
Applied sciences
Artificial intelligence
Benchmarking
binary classification problem
Cameras
Classification
Computer science; control theory; systems
Data processing. List processing. Character string processing
Exact sciences and technology
Image acquisition
Image and vision processing and display technology
image classification
image dissimilarities
image matching
image sensors
linear subspace
Memory organisation. Data processing
multiple disjoint cameras
Pattern recognition. Digital image processing. Computational geometry
PCA coefficients modelling
person reidentification
principal component analysis
signature‐based matching
Software
State of the art
Subspaces
Trains
image sensors
signature-based matching
binary classification problem
image classification
PCA coefficients modelling
person reidentification
image dissimilarities
linear subspace
multiple disjoint cameras
image matching
principal component analysis
Multiple view
Computer vision
Vector space
Similarity
Surveillance
Experimental study
Modeling
Binary classification
Principal component analysis
ISSN:0013-5194, 1350-911X, 1350-911X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0013-5194
1350-911X
1350-911X
DOI:10.1049/el.2014.0856