Learning View-Specific Deep Networks for Person Re-Identification

In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of the re-id is the serious intra-class variations caused by chang...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2018-07, Vol.27 (7), p.3472-3483
Main Authors: Feng, Zhanxiang, Lai, Jianhuang, Xie, Xiaohua
Format: Article
Language:English
Subjects:
Artificial neural networks
Benchmark testing
Cameras
Computational modeling
cross-view center loss
cross-view Euclidean constraint
Dictionaries
Feature extraction
Identification methods
Iterative algorithms
Machine learning
Measurement
Neural networks
Pedestrians
Performance enhancement
Person re-identification
view-specific deep networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of the re-id is the serious intra-class variations caused by changing viewpoints. To overcome this challenge, we propose a deep neural network-based framework which utilizes the view information in the feature extraction stage. The proposed framework learns a view-specific network for each camera view with a cross-view Euclidean constraint (CV-EC) and a cross-view center loss. We utilize the CV-EC to decrease the margin of the features between diverse views and extend the center loss metric to a view-specific version to better adapt the re-id problem. Moreover, we propose an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine. The experiments demonstrate that our approach significantly improves the performance of the existing deep networks and outperforms the state-of-the-art methods on the VIPeR, CUHK01, CUHK03, SYSU-mReId, and Market-1501 benchmarks.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2018.2818438