IMU Sensor-Based Hand Gesture Recognition for Human-Machine Interfaces

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 18; p. 3827
• Main Authors: Kim, Minwoo, Cho, Jaechan, Lee, Seongjoo, Jung, Yunho
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 04.09.2019; MDPI
• Subjects: Accuracy; Algorithms; Biosensing Techniques; dynamic time warping (DTW); Field programmable gate arrays; Gesture recognition; Gestures; Hand - physiology; hand gesture recognition (HGR); Humans; inertial measurement unit (IMU); Inertial platforms; International conferences; Machine Learning; Man-machine interfaces; Neural networks; Neural Networks, Computer; Neurons; Real time; real-time learning; Recognition; restricted coulomb energy (RCE) neural network; Sensors; User-Computer Interface; hand gesture recognition (HGR); inertial measurement unit (IMU); machine learning; dynamic time warping (DTW); restricted coulomb energy (RCE) neural network; real-time learning
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19183827

We propose an efficient hand gesture recognition (HGR) algorithm, which can cope with time-dependent data from an inertial measurement unit (IMU) sensor and support real-time learning for various human-machine interface (HMI) applications. Although the data extracted from IMU sensors are time-dependent, most existing HGR algorithms do not consider this characteristic, which results in the degradation of recognition performance. Because the dynamic time warping (DTW) technique considers the time-dependent characteristic of IMU sensor data, the recognition performance of DTW-based algorithms is better than that of others. However, the DTW technique requires a very complex learning algorithm, which makes it difficult to support real-time learning. To solve this issue, the proposed HGR algorithm is based on a restricted column energy (RCE) neural network, which has a very simple learning scheme in which neurons are activated when necessary. By replacing the metric calculation of the RCE neural network with DTW distance, the proposed algorithm exhibits superior recognition performance for time-dependent sensor data while supporting real-time learning. Our verification results on a field-programmable gate array (FPGA)-based test platform show that the proposed HGR algorithm can achieve a recognition accuracy of 98.6% and supports real-time learning and recognition at an operating frequency of 150 MHz.