Multi-view human action recognition using wavelet data reduction and multi-class classification

Human action recognition from video has several potential to apply in different real-life applications, but the most cases in this field suffer from the variation in viewpoint. Most of published methods in this area are considered the performance of each single camera, therefore the change in the vi...

Full description

Bibliographic Details
Main Authors: Aryanfar, Alihossein, Yaakob, Razali, Abdul Halin, Alfian, Sulaiman, Md. Nasir, Kasmiran, Khairul Azhar, Mohammadpour, Leila
Format: Article
Language:English
Published: Elsevier 2015
Online Access:http://psasir.upm.edu.my/id/eprint/48080/
http://psasir.upm.edu.my/id/eprint/48080/1/48080.pdf
_version_ 1848850983368523776
author Aryanfar, Alihossein
Yaakob, Razali
Abdul Halin, Alfian
Sulaiman, Md. Nasir
Kasmiran, Khairul Azhar
Mohammadpour, Leila
author_facet Aryanfar, Alihossein
Yaakob, Razali
Abdul Halin, Alfian
Sulaiman, Md. Nasir
Kasmiran, Khairul Azhar
Mohammadpour, Leila
author_sort Aryanfar, Alihossein
building UPM Institutional Repository
collection Online Access
description Human action recognition from video has several potential to apply in different real-life applications, but the most cases in this field suffer from the variation in viewpoint. Most of published methods in this area are considered the performance of each single camera, therefore the change in the viewpoints significantly decrease the recognition rate. In this paper, multiple views are considered together and a method has proposed to recognize human action depicted in multi-view image sequences. In the first step, the border of the human body's silhouette is extracted and distance signal is calculated. In the next step, the wavelet transform is applied to extract coefficients of single-view features, and then the extracted features are combined to compose multi-view features. Finally a hierarchical classifier using support vector machine and Naïve Bayes classifiers is implemented to classify the actions. The average of overall action recognition accuracy for 12 actions using 5 different angles of views on the IXMAS dataset is 88.22. The results of experiments on the popular multi-view dataset have shown the proposed method achieves high and state-of-the-art success rates. In other word, combination of single-view extracted features from the wavelet approximation coefficients and composing the multi-view features can be used as the multi-view features. Further, the hierarchical classifier can be applied to recognize actions in multi-view human action recognition area.
first_indexed 2025-11-15T10:14:57Z
format Article
id upm-48080
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:14:57Z
publishDate 2015
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling upm-480802016-08-04T08:47:52Z http://psasir.upm.edu.my/id/eprint/48080/ Multi-view human action recognition using wavelet data reduction and multi-class classification Aryanfar, Alihossein Yaakob, Razali Abdul Halin, Alfian Sulaiman, Md. Nasir Kasmiran, Khairul Azhar Mohammadpour, Leila Human action recognition from video has several potential to apply in different real-life applications, but the most cases in this field suffer from the variation in viewpoint. Most of published methods in this area are considered the performance of each single camera, therefore the change in the viewpoints significantly decrease the recognition rate. In this paper, multiple views are considered together and a method has proposed to recognize human action depicted in multi-view image sequences. In the first step, the border of the human body's silhouette is extracted and distance signal is calculated. In the next step, the wavelet transform is applied to extract coefficients of single-view features, and then the extracted features are combined to compose multi-view features. Finally a hierarchical classifier using support vector machine and Naïve Bayes classifiers is implemented to classify the actions. The average of overall action recognition accuracy for 12 actions using 5 different angles of views on the IXMAS dataset is 88.22. The results of experiments on the popular multi-view dataset have shown the proposed method achieves high and state-of-the-art success rates. In other word, combination of single-view extracted features from the wavelet approximation coefficients and composing the multi-view features can be used as the multi-view features. Further, the hierarchical classifier can be applied to recognize actions in multi-view human action recognition area. Elsevier 2015 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/48080/1/48080.pdf Aryanfar, Alihossein and Yaakob, Razali and Abdul Halin, Alfian and Sulaiman, Md. Nasir and Kasmiran, Khairul Azhar and Mohammadpour, Leila (2015) Multi-view human action recognition using wavelet data reduction and multi-class classification. Procedia Computer Science, 62. pp. 585-592. ISSN 1877-0509 http://www.sciencedirect.com/science/article/pii/S1877050915026757 10.1016/j.procs.2015.08.540
spellingShingle Aryanfar, Alihossein
Yaakob, Razali
Abdul Halin, Alfian
Sulaiman, Md. Nasir
Kasmiran, Khairul Azhar
Mohammadpour, Leila
Multi-view human action recognition using wavelet data reduction and multi-class classification
title Multi-view human action recognition using wavelet data reduction and multi-class classification
title_full Multi-view human action recognition using wavelet data reduction and multi-class classification
title_fullStr Multi-view human action recognition using wavelet data reduction and multi-class classification
title_full_unstemmed Multi-view human action recognition using wavelet data reduction and multi-class classification
title_short Multi-view human action recognition using wavelet data reduction and multi-class classification
title_sort multi-view human action recognition using wavelet data reduction and multi-class classification
url http://psasir.upm.edu.my/id/eprint/48080/
http://psasir.upm.edu.my/id/eprint/48080/
http://psasir.upm.edu.my/id/eprint/48080/
http://psasir.upm.edu.my/id/eprint/48080/1/48080.pdf