Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns
Action recognition in robotics is a research field that has gained momentum in recent years. In this work, a video activity recognition method is presented, which has the ultimate goal of endowing a robot with action recognition capabilities for a more natural social interaction. The application of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/8/2436 |
| _version_ | 1827717984590757888 |
|---|---|
| author | Itsaso Rodríguez-Moreno José María Martínez-Otzeta Izaro Goienetxea Igor Rodriguez-Rodriguez Basilio Sierra |
| author_facet | Itsaso Rodríguez-Moreno José María Martínez-Otzeta Izaro Goienetxea Igor Rodriguez-Rodriguez Basilio Sierra |
| author_sort | Itsaso Rodríguez-Moreno |
| collection | DOAJ |
| description | Action recognition in robotics is a research field that has gained momentum in recent years. In this work, a video activity recognition method is presented, which has the ultimate goal of endowing a robot with action recognition capabilities for a more natural social interaction. The application of Common Spatial Patterns (CSP), a signal processing approach widely used in electroencephalography (EEG), is presented in a novel manner to be used in activity recognition in videos taken by a humanoid robot. A sequence of skeleton data is considered as a multidimensional signal and filtered according to the CSP algorithm. Then, characteristics extracted from these filtered data are used as features for a classifier. A database with 46 individuals performing six different actions has been created to test the proposed method. The CSP-based method along with a Linear Discriminant Analysis (LDA) classifier has been compared to a Long Short-Term Memory (LSTM) neural network, showing that the former obtains similar or better results than the latter, while being simpler. |
| first_indexed | 2024-03-10T20:14:04Z |
| format | Article |
| id | doaj.art-0523cd789a264543a5eb10d538b947bc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:14:04Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0523cd789a264543a5eb10d538b947bc2023-11-19T22:39:23ZengMDPI AGSensors1424-82202020-04-01208243610.3390/s20082436Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial PatternsItsaso Rodríguez-Moreno0José María Martínez-Otzeta1Izaro Goienetxea2Igor Rodriguez-Rodriguez3Basilio Sierra4Department of Computer Science and Artificial Intelligence, University of the Basque Country, Manuel Lardizabal 1, 20018 Donostia-San Sebastián, SpainDepartment of Computer Science and Artificial Intelligence, University of the Basque Country, Manuel Lardizabal 1, 20018 Donostia-San Sebastián, SpainDepartment of Computer Science and Artificial Intelligence, University of the Basque Country, Manuel Lardizabal 1, 20018 Donostia-San Sebastián, SpainDepartment of Computer Science and Artificial Intelligence, University of the Basque Country, Manuel Lardizabal 1, 20018 Donostia-San Sebastián, SpainDepartment of Computer Science and Artificial Intelligence, University of the Basque Country, Manuel Lardizabal 1, 20018 Donostia-San Sebastián, SpainAction recognition in robotics is a research field that has gained momentum in recent years. In this work, a video activity recognition method is presented, which has the ultimate goal of endowing a robot with action recognition capabilities for a more natural social interaction. The application of Common Spatial Patterns (CSP), a signal processing approach widely used in electroencephalography (EEG), is presented in a novel manner to be used in activity recognition in videos taken by a humanoid robot. A sequence of skeleton data is considered as a multidimensional signal and filtered according to the CSP algorithm. Then, characteristics extracted from these filtered data are used as features for a classifier. A database with 46 individuals performing six different actions has been created to test the proposed method. The CSP-based method along with a Linear Discriminant Analysis (LDA) classifier has been compared to a Long Short-Term Memory (LSTM) neural network, showing that the former obtains similar or better results than the latter, while being simpler.https://www.mdpi.com/1424-8220/20/8/2436action recognitionsocial roboticscommon spatial patterns |
| spellingShingle | Itsaso Rodríguez-Moreno José María Martínez-Otzeta Izaro Goienetxea Igor Rodriguez-Rodriguez Basilio Sierra Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns Sensors action recognition social robotics common spatial patterns |
| title | Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns |
| title_full | Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns |
| title_fullStr | Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns |
| title_full_unstemmed | Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns |
| title_short | Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns |
| title_sort | shedding light on people action recognition in social robotics by means of common spatial patterns |
| topic | action recognition social robotics common spatial patterns |
| url | https://www.mdpi.com/1424-8220/20/8/2436 |
| work_keys_str_mv | AT itsasorodriguezmoreno sheddinglightonpeopleactionrecognitioninsocialroboticsbymeansofcommonspatialpatterns AT josemariamartinezotzeta sheddinglightonpeopleactionrecognitioninsocialroboticsbymeansofcommonspatialpatterns AT izarogoienetxea sheddinglightonpeopleactionrecognitioninsocialroboticsbymeansofcommonspatialpatterns AT igorrodriguezrodriguez sheddinglightonpeopleactionrecognitioninsocialroboticsbymeansofcommonspatialpatterns AT basiliosierra sheddinglightonpeopleactionrecognitioninsocialroboticsbymeansofcommonspatialpatterns |