Hand Gesture Recognition Using FSK Radar Sensors

Abstract

Hand gesture recognition, which is one of the fields of human–computer interaction (HCI) research, extracts the user’s pattern using sensors. Radio detection and ranging (RADAR) sensors are robust under severe environments and convenient to use for hand gestures. The existing studies mostly adopted continuous-wave (CW) radar, which only shows a good performance at a fixed distance, which is due to its limitation of not seeing the distance. This paper proposes a hand gesture recognition system that utilizes frequency-shift keying (FSK) radar, allowing for a recognition method that can work at the various distances between a radar sensor and a user. The proposed system adopts a convolutional neural network (CNN) model for the recognition. From the experimental results, the proposed recognition system covers the range from 30 cm to 180 cm and shows an accuracy of 93.67% over the entire range.

Static and Dynamic Hand Gestures: A Review of Techniques of Virtual Reality Manipulation

“…HCI seeks to transfer the naturalness of the interaction that occurs between people to the interaction between humans and computers, interaction that has been conditioned and limited by the use of mechanical interfaces and devices such as the mouse and keyboard [ 46 , 47 ]. Several studies, showing different architectures based on gesture recognition, present different ways of developing systems for recognition and their integration with specialized and non-specialized hardware [ 50 , 51 , 52 , 53 , 54 ]. Gestural interaction applied to technology is increasingly part of our daily life through mobile devices [ 58 , 73 , 74 ].…”

“…Several works on gesture detection were published in the 1990s. The techniques were based on several classifiers for hand gesture recognition (HGR), including the k-nearest neighbors’ algorithm, support vector machines (SVMs), neural networks (NNs), and finite-state machines (FSNs), in addition to hidden Markov models and neural networks for calibration [ 51 , 52 , 53 , 54 , 55 , 56 ]. Table 3 and Table 4 show the detection techniques for static and dynamic gestures, respectively.…”

Sign language recognition based on dual-path background erasure convolutional neural network

“…Xie et al 29 obtain multi-scale visual features by sampling video segments at different frame rates, and recognize sign language through feature fusion through attention mechanism. Yang et al 30 proposed a gesture recognition system using frequency shift keying (FSK) radar. The system uses a convolutional neural network model to recognize gestures within a certain range, breaking the limitations of gesture recognition at a fixed distance.…”