Cross-Modality Person Re-Identification Based on Heterogeneous Center Loss and Non-Local Features

Cross-modality person re-identification is the study of images of people matching under different modalities (RGB modality, IR modality). Given one RGB image of a pedestrian collected under visible light in the daytime, cross-modality person re-identification aims to determine whether the same pedes...

Full description

Saved in:
Bibliographic Details
Published in:Entropy (Basel, Switzerland) Switzerland), 2021-07, Vol.23 (7), p.919
Main Authors: Han, Chengmei, Pan, Peng, Zheng, Aihua, Tang, Jin
Format: Article
Language:English
Subjects:
Artificial neural networks
Cameras
cross-modality
Facial recognition technology
heterogeneous center loss
Identification
Infrared cameras
Infrared imagery
Infrared imaging
Light
Machine learning
Neural networks
Night
non-local
person re-identification
Similarity
Surveillance
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:Cross-modality person re-identification is the study of images of people matching under different modalities (RGB modality, IR modality). Given one RGB image of a pedestrian collected under visible light in the daytime, cross-modality person re-identification aims to determine whether the same pedestrian appears in infrared images (IR images) collected by infrared cameras at night, and vice versa. Cross-modality person re-identification can solve the task of pedestrian recognition in low light or at night. This paper aims to improve the degree of similarity for the same pedestrian in two modalities by improving the feature expression ability of the network and designing appropriate loss functions. To implement our approach, we introduce a deep neural network structure combining heterogeneous center loss (HC loss) and a non-local mechanism. On the one hand, this can heighten the performance of feature representation of the feature learning module, and, on the other hand, it can improve the similarity of cross-modality within the class. Experimental data show that the network achieves excellent performance on SYSU-MM01 datasets.
ISSN:1099-4300
1099-4300
DOI:10.3390/e23070919