Bike-Person Re-Identification: A Benchmark and a Comprehensive Evaluation

Existing person re-identification (re-id) datasets only consist of pedestrian images, which are far more behind what the real surveillance system holds. As investigated a real camera in a whole daytime, we find that there are more than 40% persons are riding bikes rather than walking. However, such...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2018, Vol.6, p.56059-56068
Hauptverfasser:	Yuan, Yuan, Zhang, Jian'an, Wang, Qi
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Benchmark testing Benchmarks Bicycles Bike-person re-identification Cameras Datasets Feature extraction Machine learning Measurement Pipeline design Pipelines re-identification re-identification dataset splitting method Surveillance Walking
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!