In this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets. The primary research goal was to define the most appropriate model architecture in terms of the accurate recognition of each gesture. An additional aim of the research was to investigate the kind of input data, i.e., raw data or preprocessed (feature) data, which generally produces better results. Therefore, three datasets were generated: raw data, simple features data, and high-level features data. (This includes information about hand poses which are already recognized.) The random search method was applied to achieve hyperparameter optimization to find the best possible topology for the neural network. The analysis performed shows that selected models were characterized by a test score at a level of 96.89% for the raw data, 95.75% for simple features, and 93.38% for high-level features. Results indicate that the direct use of raw data obtained from the optical linear sensor evaluated on the RNN with GRU memory cells allows for the reliable recognition of even complex gestures. Therefore, such solutions may have the potential to serve as a support to or as an alternative to video-based sensors especially for mobile devices.
Web of Science
- Publikacja w czasopiśmie
- artykuł w czasopiśmie wyróżnionym w JCR
- Opublikowano w:
IEEE SENSORS JOURNAL
strony 5429 - 5438,
- Rok wydania:
- Opis bibliograficzny:
- Czuszyński K., Rumiński J., Kwaśniewska A.: Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks// IEEE SENSORS JOURNAL. -Vol. 18, iss. 13 (2018), s.5429-5438
- Cyfrowy identyfikator dokumentu elektronicznego (otwiera się w nowej karcie) 10.1109/jsen.2018.2834968
- Źródła finansowania:
- This work was supported by NCBiR, FWF, SNSF, ANR, and FNR in the framework of ERA-NET CHIST-ERA II through Project eGLASSES—The interactive eyeglasses for mobile, perceptual computing, and in part by Statutory Funds of the Electronics, Telecommunications and Informatics Faculty, Gdansk University of Technology.
wyświetlono 15 razy