A Flexible Data Set for Radar-based Gesture Recognition with an FC-FMCW Radar
Antes, Theresa
1; Bekker, Elizabeth 1; Bhutani, Akanksha
1; Zwick, Thomas 1
1 Institut für Hochfrequenztechnik und Elektronik (IHE), Karlsruher Institut für Technologie (KIT)
1; Bekker, Elizabeth 1; Bhutani, Akanksha
1; Zwick, Thomas 11 Institut für Hochfrequenztechnik und Elektronik (IHE), Karlsruher Institut für Technologie (KIT)
Abstract (englisch):
A broad and flexible data set for radar-based gesture recognition of 7 gestures using a fast chirp frequency-modulated continuous wave (FC-FMCW) radar is made available. A legend containing information about the provided data set and its recordings to enable informed usage by third parties is provided alongside.
| Zugehörige Institution(en) am KIT | Institut für Hochfrequenztechnik und Elektronik (IHE) |
| Publikationstyp | Forschungsdaten |
| Publikationsdatum | 02.10.2024 |
| Erstellungsdatum | 01.07.2022 - 31.01.2024 |
| Identifikator | DOI: 10.35097/hCNNxXlJBdFTSYse KITopen-ID: 1000172790 |
| Lizenz | Creative Commons Namensnennung 4.0 International |
| Schlagwörter | data set, FC-FMCW radar, gesture recognition, human hand gestures, radar sensing |
| Liesmich | The data set contains 2479 recordings from 25 individuals performing 7 different gestures and zero-class measurements. It is split into two parts. The first part (924 recordings from 22 participants) contains recordings of 7 gestures. The second part (1555 recordings from 4 participants) includes 5 gestures and additional zero-class measurements with no or random movement to be distinguished from actual gestures. Each recording has a unique designation with an underscored separation between its attributes. The available attributes contain information about the gesture, measurement setup, and personal information about the individual performing the gesture. All gestures were captured using a BGT60TR13C radar sensor by Infineon. |
| Art der Forschungsdaten | Dataset |