Improving Hand Gesture Recognition Robustness to Dynamic Posture Variations by Multimodal Deep Feature Fusion.
IEEE Trans Neural Syst Rehabil Eng
; 32: 3104-3115, 2024.
Article
en En
| MEDLINE
| ID: mdl-39172614
ABSTRACT
Surface electromyography (sEMG), a human-machine interface for gesture recognition, has shown promising potential for decoding motor intentions, but a variety of nonideal factors restrict its practical application in assistive robots. In this paper, we summarized the current mainstream gesture recognition strategies and proposed a gesture recognition method based on multimodal canonical correlation analysis feature fusion classification (MCAFC) for a nonideal condition that occurs in daily life, i.e., posture variations. The deep features of the sEMG and acceleration signals were first extracted via convolutional neural networks. A canonical correlation analysis was subsequently performed to associate the deep features of the two modalities. The transformed features were utilized as inputs to a linear discriminant analysis classifier to recognize the corresponding gestures. Both offline and real-time experiments were conducted on eight non-disabled subjects. The experimental results indicated that MCAFC achieved an average classification accuracy, average motion completion rate, and average motion completion time of 93.44%, 94.05%, and 1.38 s, respectively, with multiple dynamic postures, indicating significantly better performance than that of comparable methods. The results demonstrate the feasibility and superiority of the proposed multimodal signal feature fusion method for gesture recognition with posture variations, providing a new scheme for myoelectric control.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Postura
/
Algoritmos
/
Reconocimiento de Normas Patrones Automatizadas
/
Redes Neurales de la Computación
/
Electromiografía
/
Gestos
/
Mano
Límite:
Adult
/
Female
/
Humans
/
Male
Idioma:
En
Revista:
IEEE Trans Neural Syst Rehabil Eng
Asunto de la revista:
ENGENHARIA BIOMEDICA
/
REABILITACAO
Año:
2024
Tipo del documento:
Article
Pais de publicación:
Estados Unidos