Title :
Human Action Recognition by Radon Transform
Author :
Chen, Yan ; Wu, Qiang ; He, Xiangjian
Author_Institution :
Centre for Innovation in IT Services & Applic., Univ. of Technol., Sydney, NSW
Abstract :
A new feature description is used for human behaviour representation and recognition. The feature is based on Radon transforms of extracted silhouettes. Key postures are selected based on the Radon transform. Key postures are combined to construct an action template for each sequence. Linear discriminant analysis (LDA) is applied to the set of key postures to obtain low dimensional feature vectors. Different classification methods are used to classify each sequence. Experiments are carried out based on a publically available human behaviour database and the results are exciting.
Keywords :
Radon transforms; feature extraction; image classification; image representation; image sequences; object recognition; vectors; Radon transform; action template; feature description; feature vector; human action recognition; human behaviour representation; image classification; image sequence; key posture selection; linear discriminant analysis; silhouette extraction; Conferences; Data mining; Entropy; Helium; Hidden Markov models; Humans; Linear discriminant analysis; Shape; Technological innovation; Video compression; Radon transform; action recognition;
Conference_Titel :
Data Mining Workshops, 2008. ICDMW '08. IEEE International Conference on
Conference_Location :
Pisa
Print_ISBN :
978-0-7695-3503-6
Electronic_ISBN :
978-0-7695-3503-6
DOI :
10.1109/ICDMW.2008.26