Recognizing human actions from video sequences using invariant shape

Author

Chen, Xian-gan ; Liu, Juan ; Gao, Zhiyong ; Liu, Haihua

Author_Institution

Sch. of Comput., Wuhan Univ., Wuhan, China

fYear

2011

fDate

15-17 April 2011

Firstpage

1564

Lastpage

1567

Abstract

In this paper, recognizing human actions has been investigated from video sequences. With morphological gradient and pooling operation, invariant shape of each human body in an action sequence is obtained. Edge feature of invariant shape is extracted to represent human actions. Pyramid Histograms of Orientation Gradients (PHOG) of all invariant shapes in video are averaged to form a feature vector that captures the characteristic of human actions in this video sequence. Using Support Vector Machine (SVM), the method is tested on the KTH action dataset. The obtained impressive results show that invariant shape is more effective than original video in human action recognition.

Keywords

gesture recognition; gradient methods; image motion analysis; image sequences; support vector machines; vectors; video signal processing; KTH action dataset; PHOG; SVM; action sequence; edge feature; feature vector; human action recognition; human actions; human body; invariant shape; morphological gradient; pooling operation; pyramid histograms of orientation gradients; support vector machine; video sequences; Histograms; Humans; Image edge detection; Pixel; Shape; Support vector machines; Video sequences; action recognition; edge feature; invariant shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Electric Information and Control Engineering (ICEICE), 2011 International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-8036-4

Type

conf

DOI

10.1109/ICEICE.2011.5777874

Filename

5777874