Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System
In this paper, we propose a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS) for accurate detection of human actions from video sequences. In this paper, we employ optical flow based features as they can represent information from local pixel level to global object level between two consecutive i...
| Главные авторы: | , |
|---|---|
| Другие авторы: | |
| Формат: | Conference Paper |
| Язык: | English |
| Опубликовано: |
2013
|
| Предметы: | |
| Online-ссылка: | https://hdl.handle.net/10356/97942 http://hdl.handle.net/10220/12382 |
| _version_ | 1826124582305660928 |
|---|---|
| author | Suresh, Sundaram Subramanian, K. |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Suresh, Sundaram Subramanian, K. |
| author_sort | Suresh, Sundaram |
| collection | NTU |
| description | In this paper, we propose a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS) for accurate detection of human actions from video sequences. In this paper, we employ optical flow based features as they can represent information from local pixel level to global object level between two consecutive image planes. The functional relationship between these optical flow based features and action classes is approximated using McFIS classifier. The sequential learning algorithm is developed based on the principles of self-regulation observed in human meta-cognition. McFIS decides on what-to-learn, when-to-learn and how-to-learn based on the knowledge stored in the classifier and the information contained in the new training sample. The sequential learning algorithm of McFIS is controlled and monitored by the meta-cognitive components which uses class-specific and knowledge based criteria along with self-regulatory thresholds to decide on one of the following strategies: a) sample deletion b) sample learning and c) sample reserve. Performance of proposed McFIS based human action recognition system is evaluated using benchmark Weizmann and KTH video sequences. The simulation results are compared with well known support vector machine classifier and also with state-of-the-art action recognition results reported in the literature. The results clearly indicates McFIS action recognition system achieves better performances with minimal computational effort. |
| first_indexed | 2024-10-01T06:22:45Z |
| format | Conference Paper |
| id | ntu-10356/97942 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:22:45Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/979422020-05-28T07:17:53Z Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System Suresh, Sundaram Subramanian, K. School of Computer Engineering International Joint Conference on Neural Networks (2012 : Brisbane, Australia) DRNTU::Engineering::Computer science and engineering In this paper, we propose a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS) for accurate detection of human actions from video sequences. In this paper, we employ optical flow based features as they can represent information from local pixel level to global object level between two consecutive image planes. The functional relationship between these optical flow based features and action classes is approximated using McFIS classifier. The sequential learning algorithm is developed based on the principles of self-regulation observed in human meta-cognition. McFIS decides on what-to-learn, when-to-learn and how-to-learn based on the knowledge stored in the classifier and the information contained in the new training sample. The sequential learning algorithm of McFIS is controlled and monitored by the meta-cognitive components which uses class-specific and knowledge based criteria along with self-regulatory thresholds to decide on one of the following strategies: a) sample deletion b) sample learning and c) sample reserve. Performance of proposed McFIS based human action recognition system is evaluated using benchmark Weizmann and KTH video sequences. The simulation results are compared with well known support vector machine classifier and also with state-of-the-art action recognition results reported in the literature. The results clearly indicates McFIS action recognition system achieves better performances with minimal computational effort. 2013-07-26T06:15:51Z 2019-12-06T19:48:35Z 2013-07-26T06:15:51Z 2019-12-06T19:48:35Z 2012 2012 Conference Paper Subramanian, K., & Suresh, S. (2012). Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System. The 2012 International Joint Conference on Neural Networks (IJCNN). https://hdl.handle.net/10356/97942 http://hdl.handle.net/10220/12382 10.1109/IJCNN.2012.6252623 en © 2012 IEEE. |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Suresh, Sundaram Subramanian, K. Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title | Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title_full | Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title_fullStr | Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title_full_unstemmed | Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title_short | Human action recognition using Meta-Cognitive Neuro-Fuzzy Inference System |
| title_sort | human action recognition using meta cognitive neuro fuzzy inference system |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/97942 http://hdl.handle.net/10220/12382 |
| work_keys_str_mv | AT sureshsundaram humanactionrecognitionusingmetacognitiveneurofuzzyinferencesystem AT subramaniank humanactionrecognitionusingmetacognitiveneurofuzzyinferencesystem |