Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier

Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i....

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2017-10, Vol.26 (10), p.4648-4660
Hauptverfasser:	Zhang, Baochang, Yang, Yun, Chen, Chen, Yang, Linlin, Han, Jungong, Shao, Ling
Format:	Artikel
Sprache:	eng
Schlagworte:	Action recognition Boosting boosting classifier Cartesian coordinates Classification algorithms Classifiers depth image Feature extraction Hidden Markov models Histograms Human motion Moving object recognition multi-class classification Planes Robustness texture feature Texture recognition Three-dimensional displays
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!