An enhanced method for human action recognition
This paper presents a fast and simple method for human action recognition. The proposed technique relies on detecting interest points using SIFT (scale invariant feature transform) from each frame of the video. A fine-tuning step is used here to limit the number of interesting points according to th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2015-03-01
|
| Series: | Journal of Advanced Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090123213001434 |
| _version_ | 1819138260876656640 |
|---|---|
| author | Mona M. Moussa Elsayed Hamayed Magda B. Fayek Heba A. El Nemr |
| author_facet | Mona M. Moussa Elsayed Hamayed Magda B. Fayek Heba A. El Nemr |
| author_sort | Mona M. Moussa |
| collection | DOAJ |
| description | This paper presents a fast and simple method for human action recognition. The proposed technique relies on detecting interest points using SIFT (scale invariant feature transform) from each frame of the video. A fine-tuning step is used here to limit the number of interesting points according to the amount of details. Then the popular approach Bag of Video Words is applied with a new normalization technique. This normalization technique remarkably improves the results. Finally a multi class linear Support Vector Machine (SVM) is utilized for classification. Experiments were conducted on the KTH and Weizmann datasets. The results demonstrate that our approach outperforms most existing methods, achieving accuracy of 97.89% for KTH and 96.66% for Weizmann. |
| first_indexed | 2024-12-22T11:03:57Z |
| format | Article |
| id | doaj.art-9ace80307d9642418070b92f357b06f3 |
| institution | Directory Open Access Journal |
| issn | 2090-1232 2090-1224 |
| language | English |
| last_indexed | 2024-12-22T11:03:57Z |
| publishDate | 2015-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Advanced Research |
| spelling | doaj.art-9ace80307d9642418070b92f357b06f32022-12-21T18:28:24ZengElsevierJournal of Advanced Research2090-12322090-12242015-03-016216316910.1016/j.jare.2013.11.007An enhanced method for human action recognitionMona M. Moussa0Elsayed Hamayed1Magda B. Fayek2Heba A. El Nemr3Computers and Systems Department, Electronics Research Institute, EgyptComputer Engineering Department, Faculty of Engineering, Cairo University, EgyptComputer Engineering Department, Faculty of Engineering, Cairo University, EgyptComputers and Systems Department, Electronics Research Institute, EgyptThis paper presents a fast and simple method for human action recognition. The proposed technique relies on detecting interest points using SIFT (scale invariant feature transform) from each frame of the video. A fine-tuning step is used here to limit the number of interesting points according to the amount of details. Then the popular approach Bag of Video Words is applied with a new normalization technique. This normalization technique remarkably improves the results. Finally a multi class linear Support Vector Machine (SVM) is utilized for classification. Experiments were conducted on the KTH and Weizmann datasets. The results demonstrate that our approach outperforms most existing methods, achieving accuracy of 97.89% for KTH and 96.66% for Weizmann.http://www.sciencedirect.com/science/article/pii/S2090123213001434SIFTAction recognitionBag of wordsSVM |
| spellingShingle | Mona M. Moussa Elsayed Hamayed Magda B. Fayek Heba A. El Nemr An enhanced method for human action recognition Journal of Advanced Research SIFT Action recognition Bag of words SVM |
| title | An enhanced method for human action recognition |
| title_full | An enhanced method for human action recognition |
| title_fullStr | An enhanced method for human action recognition |
| title_full_unstemmed | An enhanced method for human action recognition |
| title_short | An enhanced method for human action recognition |
| title_sort | enhanced method for human action recognition |
| topic | SIFT Action recognition Bag of words SVM |
| url | http://www.sciencedirect.com/science/article/pii/S2090123213001434 |
| work_keys_str_mv | AT monammoussa anenhancedmethodforhumanactionrecognition AT elsayedhamayed anenhancedmethodforhumanactionrecognition AT magdabfayek anenhancedmethodforhumanactionrecognition AT hebaaelnemr anenhancedmethodforhumanactionrecognition AT monammoussa enhancedmethodforhumanactionrecognition AT elsayedhamayed enhancedmethodforhumanactionrecognition AT magdabfayek enhancedmethodforhumanactionrecognition AT hebaaelnemr enhancedmethodforhumanactionrecognition |