Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data
In this paper we present an approach towards real-time hand gesture recognition using the Kinect sensor, investigating several machine learning techniques. We propose a novel approach for feature extraction, using measurements on joints of the extracted skeletons. The proposed features extract angle...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/12/5/108 |
| _version_ | 1824026931483377664 |
|---|---|
| author | Georgios Paraskevopoulos Evaggelos Spyrou Dimitrios Sgouropoulos Theodoros Giannakopoulos Phivos Mylonas |
| author_facet | Georgios Paraskevopoulos Evaggelos Spyrou Dimitrios Sgouropoulos Theodoros Giannakopoulos Phivos Mylonas |
| author_sort | Georgios Paraskevopoulos |
| collection | DOAJ |
| description | In this paper we present an approach towards real-time hand gesture recognition using the Kinect sensor, investigating several machine learning techniques. We propose a novel approach for feature extraction, using measurements on joints of the extracted skeletons. The proposed features extract angles and displacements of skeleton joints, as the latter move into a 3D space. We define a set of gestures and construct a real-life data set. We train gesture classifiers under the assumptions that they shall be applied and evaluated to both known and unknown users. Experimental results with 11 classification approaches prove the effectiveness and the potential of our approach both with the proposed dataset and also compared to state-of-the-art research works. |
| first_indexed | 2024-12-19T11:18:51Z |
| format | Article |
| id | doaj.art-854c4fe4eecc4dfc9d0251bf115306c7 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-12-19T11:18:51Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-854c4fe4eecc4dfc9d0251bf115306c72022-12-21T20:23:56ZengMDPI AGAlgorithms1999-48932019-05-0112510810.3390/a12050108a12050108Real-Time Arm Gesture Recognition Using 3D Skeleton Joint DataGeorgios Paraskevopoulos0Evaggelos Spyrou1Dimitrios Sgouropoulos2Theodoros Giannakopoulos3Phivos Mylonas4School of Electrical and Computer Engineering, National Technical University of Athens, Iroon Polytechneiou 9, 157 73 Zografou, GreeceInstitute of Informatics and Telecommunications, NCSR Demokritos, Neapoleos 10, 153 41 Ag. Paraskevi, GreeceInstitute of Informatics and Telecommunications, NCSR Demokritos, Neapoleos 10, 153 41 Ag. Paraskevi, GreeceInstitute of Informatics and Telecommunications, NCSR Demokritos, Neapoleos 10, 153 41 Ag. Paraskevi, GreeceDepartment of Informatics, Ionian University, Platia Tsirigoti 7, 491 00 Corfu, GreeceIn this paper we present an approach towards real-time hand gesture recognition using the Kinect sensor, investigating several machine learning techniques. We propose a novel approach for feature extraction, using measurements on joints of the extracted skeletons. The proposed features extract angles and displacements of skeleton joints, as the latter move into a 3D space. We define a set of gestures and construct a real-life data set. We train gesture classifiers under the assumptions that they shall be applied and evaluated to both known and unknown users. Experimental results with 11 classification approaches prove the effectiveness and the potential of our approach both with the proposed dataset and also compared to state-of-the-art research works.https://www.mdpi.com/1999-4893/12/5/108gesture recognitionKinectskeleton jointsmachine learning |
| spellingShingle | Georgios Paraskevopoulos Evaggelos Spyrou Dimitrios Sgouropoulos Theodoros Giannakopoulos Phivos Mylonas Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data Algorithms gesture recognition Kinect skeleton joints machine learning |
| title | Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data |
| title_full | Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data |
| title_fullStr | Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data |
| title_full_unstemmed | Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data |
| title_short | Real-Time Arm Gesture Recognition Using 3D Skeleton Joint Data |
| title_sort | real time arm gesture recognition using 3d skeleton joint data |
| topic | gesture recognition Kinect skeleton joints machine learning |
| url | https://www.mdpi.com/1999-4893/12/5/108 |
| work_keys_str_mv | AT georgiosparaskevopoulos realtimearmgesturerecognitionusing3dskeletonjointdata AT evaggelosspyrou realtimearmgesturerecognitionusing3dskeletonjointdata AT dimitriossgouropoulos realtimearmgesturerecognitionusing3dskeletonjointdata AT theodorosgiannakopoulos realtimearmgesturerecognitionusing3dskeletonjointdata AT phivosmylonas realtimearmgesturerecognitionusing3dskeletonjointdata |