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.

In order to avoid car crashes, active safety systems are becoming more and more important. Many crashes are caused due to driver drowsiness or mobile phone usage. Detecting the drowsiness of the driver is very important for the safety of a car. Monitoring of vital signs such as respiration rate and heart rate is important to determine the occurrence of driver drowsiness. In this paper, robust vital signs monitoring through impulse radio ultra-wideband (IR-UWB) radar is discussed. We propose a new algorithm that can estimate the vital signs even if there is motion caused by the driving activities. We analyzed the whole fast time vital detection region and found the signals at those fast time locations that have useful information related to the vital signals. We segmented those signals into sub-signals and then constructed the desired vital signal using the correlation method. In this way, the vital signs of the driver can be monitored noninvasively, which can be used by researchers to detect the drowsiness of the driver which is related to the vital signs i.e., respiration and heart rate. In addition, texting on a mobile phone during driving may cause visual, manual or cognitive distraction of the driver. In order to reduce accidents caused by a distracted driver, we proposed an algorithm that can detect perfectly a driver's mobile phone usage even if there are various motions of the driver in the car or changes in background objects. These novel techniques, which monitor vital signs associated with drowsiness and detect phone usage before a driver makes a mistake, may be very helpful in developing techniques for preventing a car crash.

Modern cars continue to offer more and more functionalities due to which they need a growing number of commands. As the driver tries to monitor the road and the graphic user interface simultaneously, his/her overall efficiency is reduced. In order to reduce the visual attention necessary for monitoring, a gesture-based user interface is very important. In this paper, gesture recognition for a vehicle through impulse radio ultra-wideband (IR-UWB) radar is discussed. The gestures can be used to control different electronic devices inside a vehicle. The gestures are based on human hand and finger motion. We have implemented a real-time version using only one radar sensor. Studies on gesture recognition using IR-UWB radar have rarely been carried out, and some studies are merely simple methods using the magnitude of the reflected signal or those whose performance deteriorates largely due to changes in distance or direction. In this study, we propose a new hand-based gesture recognition algorithm that works robustly against changes in distance or direction while responding only to defined gestures by ignoring meaningless motions. We used three independent features, i.e., variance of the probability density function (pdf) of the magnitude histogram, time of arrival (TOA) variation and the frequency of the reflected signal, to classify the gestures. A data fitting method is included to differentiate between gesture signals and unintended hand or body motions. We have used the clustering technique for the classification of the gestures. Moreover, the distance information is used as an additional input parameter to the clustering algorithm, such that the recognition technique will not be vulnerable to distance change. The hand-based gesture recognition proposed in this paper would be a key technology of future automobile user interfaces.