Human–Computer Interfaces (HCI) deals with the study of interface between humans and computers. The use of radar and other RF sensors to develop HCI based on Hand Gesture Recognition (HGR) has gained increasing attention over the past decade. Today, devices have built-in radars for recognizing and categorizing hand movements. In this article, we present the first ever review related to HGR using radar sensors. We review the available techniques for multi-domain hand gestures data representation for different signal processing and deep-learning-based HGR algorithms. We classify the radars used for HGR as pulsed and continuous-wave radars, and both the hardware and the algorithmic details of each category is presented in detail. Quantitative and qualitative analysis of ongoing trends related to radar-based HCI, and available radar hardware and algorithms is also presented. At the end, developed devices and applications based on gesture-recognition through radar are discussed. Limitations, future aspects and research directions related to this field are also discussed.

In this paper, we propose a people counting algorithm using an impulse radio ultra-wideband radar sensor. The proposed algorithm is based on a strategy of understanding the pattern of the received signal according to the number of people, not detecting each of a large number of people in the radar's received signal. To understand the pattern of the signal, we detect the major clusters from the signal and find the amplitudes of main pulses having the maximum amplitude among the pulses constituting each cluster. We generate a probability density function of the amplitudes of the main pulses from the major clusters according to the number of people and distances. Then, we derive maximum likelihood (ML) equation for people counting. Using the derived ML equation, real-time people counting is possible with a small amount of computation. In addition, since the proposed algorithm does not detect individual clusters for each person but based on the overall cluster behavior of the signals according to the number of people, it enables people counting even in a dense multipath environment, such as a metal-rich environment. In order to prove that the proposed algorithm can be operated in real time in various environments, we performed experiments in an indoor environment and an elevator with a metal structure. Experimental results show that people counting is performed with an mean absolute error of less than one person on average.

The vital sign monitoring through Impulse Radio Ultra-Wide Band (IR-UWB) radar provides continuous assessment of a patient’s respiration and heart rates in a non-invasive manner. In this paper, IR UWB radar is used for monitoring respiration and the human heart rate. The breathing and heart rate frequencies are extracted from the signal reflected from the human body. A Kalman filter is applied to reduce the measurement noise from the vital signal. An algorithm is presented to separate the heart rate signal from the breathing harmonics. An auto-correlation based technique is applied for detecting random body movements (RBM) during the measurement process. Experiments were performed in different scenarios in order to show the validity of the algorithm. The vital signs were estimated for the signal reflected from the chest, as well as from the back side of the body in different experiments. The results from both scenarios are compared for respiration and heartbeat estimation accuracy.

In this study, we classify digits written in mid-air using hand gestures. Impulse radio ultra-wideband (IR-UWB) radar sensors are used for data acquisition, with three radar sensors placed in a triangular geometry. Conventional radar-based gesture recognition methods use whole raw data matrices or a group of features for gesture classification using convolutional neural networks (CNNs) or other machine learning algorithms. However, if the training and testing data differ in distance, orientation, hand shape, hand size, or even gesture speed or the radar setup environment, these methods become less accurate. To develop a more robust gesture recognition method, we propose not using raw data for the CNN classifier, but instead employing the hand’s mid-air trajectory for classification. The hand trajectory has a stereotypical shape for a given digit, regardless of the hand’s orientation or speed, making its classification easy and robust. Our proposed method consists of three stages: signal preprocessing, hand motion localization, and tracking and transforming the trajectory data into an image to classify it using a CNN. Our proposed method outperforms conventional approaches because it is robust to changes in orientation, distance, and hand shape and size. Moreover, this method does not require building a huge training database of digits drawn by different users in different orientations; rather, we can use training databases already available in the image processing field. Overall, the proposed mid-air handwritten digit recognition system provides a user-friendly and accurate mid-air handwriting modality that does not place restrictions on users.

We discovered that impulse-radio ultra-wideband (IR-UWB) radar could recognize cardiac motions in a non-contact fashion. Therefore, we measured the heart rate (HR) and rhythms using an IR-UWB radar sensor and evaluated the validity and reliability of the measurements in comparison to electrocardiography. The heart beats were measured in 6 healthy volunteers (18 samples) with normal sinus rhythm (NSR) and 16 patients (36 samples) with atrial fibrillation (AF) using both an IR-UWB radar sensor and electrocardiography simultaneously. The participants hold their breath for 20 seconds during the data acquisition. In subjects with NSR, there was excellent agreement of HR (intraclass correlation coefficient [ICC] 0.856), average R-R interval (ICC 0.997) and individual R-R intervals between the two methods (ICC 0.803). In subjects with AF, HR (ICC 0.871) and average R-R interval (ICC 0.925) from the radar sensor also agreed well with those from electrocardiography, though there was a small disagreement in the individual R-R intervals between the two methods (ICC 0.697). The rhythms computed by the signal-processing algorithm showed good agreement between the two methods (Cohen’s Kappa 0.922). The IR-UWB radar sensor is precise and accurate for assessing HR and rhythms in a non-contact fashion.