Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition

This paper describes the world’s largest gait database with wide view variation, the “OU-ISIR gait database, multi-view large population dataset (OU-MVLP)”, and its application to a statistically reliable performance evaluation of vision-based cross-view gait recognition. Specifically, we construct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IPSJ transactions on computer vision and applications Jg. 10; H. 1; S. 1 - 14
Hauptverfasser: Takemura, Noriko, Makihara, Yasushi, Muramatsu, Daigo, Echigo, Tomio, Yagi, Yasushi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 20.02.2018
Springer Nature B.V
Schlagworte:
Artificial Intelligence
Computer Imaging
Computer Science
Datasets
Gait recognition
Image Processing and Computer Vision
Pattern Recognition and Graphics
Performance evaluation
Population (statistical)
Research Paper
Robotics and Automation
Statistical methods
User Interfaces and Human Computer Interaction
Vision
Multi-view large population performance evaluation
Gait recognition
Gait database
ISSN:1882-6695, 1882-6695
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper describes the world’s largest gait database with wide view variation, the “OU-ISIR gait database, multi-view large population dataset (OU-MVLP)”, and its application to a statistically reliable performance evaluation of vision-based cross-view gait recognition. Specifically, we construct a gait dataset that includes 10,307 subjects (5114 males and 5193 females) from 14 view angles ranging 0° −90°, 180° −270°. In addition, we evaluate various approaches to gait recognition which are robust against view angles. By using our dataset, we can fully exploit a state-of-the-art method requiring a large number of training samples, e.g., CNN-based cross-view gait recognition method, and we validate effectiveness of such a family of the methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1882-6695
1882-6695
DOI:10.1186/s41074-018-0039-6