A fast approach for human action recognition
This paper presents a fast approach to represent and recognize human actions. For representation, a feature vector is constructed from spatiotemporal data of silhouettes based on appearance and motion. For classification, a new Radial Basis Function Network (RBF), called Time Delay Input Radial Basi...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/41158/ http://psasir.upm.edu.my/id/eprint/41158/1/A%20fast%20approach%20for%20human%20action%20recognition.pdf |
| _version_ | 1848849620311998464 |
|---|---|
| author | Kalhor, Davood Aris, Ishak Abdul Halin, Izhal Moaini, Trifa |
| author_facet | Kalhor, Davood Aris, Ishak Abdul Halin, Izhal Moaini, Trifa |
| author_sort | Kalhor, Davood |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This paper presents a fast approach to represent and recognize human actions. For representation, a feature vector is constructed from spatiotemporal data of silhouettes based on appearance and motion. For classification, a new Radial Basis Function Network (RBF), called Time Delay Input Radial Basis Function Network is proposed by introducing time delay units to the RBF in a novel approach. The proposed network has a few desirable features such as easier learning process and more flexibility. The representational power and speed of the proposed method for action recognition were evaluated using a publicly available dataset. Based on experimental results, implemented in MATLAB and on standard PCs, the average time for constructing a feature vector for a high-resolution video is almost 20 ms/frame. Furthermore, the proposed approach demonstrates good performance in terms of execution time and overall performance (a new performance measure that combines accuracy and speed into one metric). |
| first_indexed | 2025-11-15T09:53:17Z |
| format | Conference or Workshop Item |
| id | upm-41158 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T09:53:17Z |
| publishDate | 2014 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-411582017-10-30T06:19:33Z http://psasir.upm.edu.my/id/eprint/41158/ A fast approach for human action recognition Kalhor, Davood Aris, Ishak Abdul Halin, Izhal Moaini, Trifa This paper presents a fast approach to represent and recognize human actions. For representation, a feature vector is constructed from spatiotemporal data of silhouettes based on appearance and motion. For classification, a new Radial Basis Function Network (RBF), called Time Delay Input Radial Basis Function Network is proposed by introducing time delay units to the RBF in a novel approach. The proposed network has a few desirable features such as easier learning process and more flexibility. The representational power and speed of the proposed method for action recognition were evaluated using a publicly available dataset. Based on experimental results, implemented in MATLAB and on standard PCs, the average time for constructing a feature vector for a high-resolution video is almost 20 ms/frame. Furthermore, the proposed approach demonstrates good performance in terms of execution time and overall performance (a new performance measure that combines accuracy and speed into one metric). IEEE 2014 Conference or Workshop Item NonPeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/41158/1/A%20fast%20approach%20for%20human%20action%20recognition.pdf Kalhor, Davood and Aris, Ishak and Abdul Halin, Izhal and Moaini, Trifa (2014) A fast approach for human action recognition. In: Fifth International Conference on Intelligent Systems, Modelling and Simulation (ISMS 2014), 27-29 Jan. 2014, Langkawi, Kedah, Malaysia. (pp. 266-272). 10.1109/ISMS.2014.52 |
| spellingShingle | Kalhor, Davood Aris, Ishak Abdul Halin, Izhal Moaini, Trifa A fast approach for human action recognition |
| title | A fast approach for human action recognition |
| title_full | A fast approach for human action recognition |
| title_fullStr | A fast approach for human action recognition |
| title_full_unstemmed | A fast approach for human action recognition |
| title_short | A fast approach for human action recognition |
| title_sort | fast approach for human action recognition |
| url | http://psasir.upm.edu.my/id/eprint/41158/ http://psasir.upm.edu.my/id/eprint/41158/ http://psasir.upm.edu.my/id/eprint/41158/1/A%20fast%20approach%20for%20human%20action%20recognition.pdf |