Efficient HOG human detection

While Histograms of Oriented Gradients (HOG) plus Support Vector Machine (SVM) (HOG+SVM) is the most successful human detection algorithm, it is time-consuming. This paper proposes two ways to deal with this problem. One way is to reuse the features in blocks to construct the HOG features for inters...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal processing Jg. 91; H. 4; S. 773 - 781
Hauptverfasser: Pang, Yanwei, Yuan, Yuan, Li, Xuelong, Pan, Jing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.04.2011
Elsevier
Schlagworte:
Algorithms
Applied sciences
Construction
Exact sciences and technology
Fast algorithm
Histograms
HOG
Human
Human detection
Image and video processing
Image processing
Information, signal and communications theory
Interpolation
Pattern recognition
Reuse
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Support vector machines
Telecommunications and information theory
HOG
Image and video processing
Fast algorithm
Human detection
Performance evaluation
Automatic classification
Histogram
Image processing
Support vector machine
Pattern recognition
Signal classification
Video signal processing
Interpolation
One way
Database
ISSN:0165-1684, 1872-7557
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:While Histograms of Oriented Gradients (HOG) plus Support Vector Machine (SVM) (HOG+SVM) is the most successful human detection algorithm, it is time-consuming. This paper proposes two ways to deal with this problem. One way is to reuse the features in blocks to construct the HOG features for intersecting detection windows. Another way is to utilize sub-cell based interpolation to efficiently compute the HOG features for each block. The combination of the two ways results in significant increase in detecting humans—more than five times better. To evaluate the proposed method, we have established a top-view human database. Experimental results on the top-view database and the well-known INRIA data set have demonstrated the effectiveness and efficiency of the proposed method.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0165-1684
1872-7557
DOI:10.1016/j.sigpro.2010.08.010