Robust CoHOG Feature Extraction in Human-Centered Image/Video Management System

Many human-centered image and video management systems depend on robust human detection. To extract robust features for human detection, this paper investigates the following shortcomings of co-occurrence histograms of oriented gradients (CoHOGs) which significantly limit its advantages: (1) The mag...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on cybernetics 2012-04, Vol.42 (2), p.458-468
Hauptverfasser:	Pang, Yanwei, Yan, He, Yuan, Yuan, Wang, Kongqiao
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Co-occurrence histograms of oriented gradients (CoHOGs) Convolution Cybernetics Databases, Factual Feature extraction Histograms histograms of oriented gradients (HOGs) Human Human Activities human detection human-centered image retrieval Humans Image Processing, Computer-Assisted - methods Interpolation Management systems Mathematical analysis Pattern Recognition, Automated - methods Principal Component Analysis Principal components analysis Robustness Strategy Studies Vectors Vectors (mathematics)
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!