Short-range FMCW monopulse radar for hand-gesture sensing

Abstract

Intelligent driver assistance systems have become important in the automotive industry. One key element of such systems is a smart user interface that tracks and recognizes drivers' hand gestures. Hand gesture sensing using traditional computer vision techniques is challenging because of wide variations in lighting conditions, e.g. inside a car. A short-range radar device can provide additional information, including the location and instantaneous radial velocity of moving objects. We describe a novel end-to-end (hardware, interface, and software) short-range FMCW radar-based system designed to effectively sense dynamic hand gestures. We provide an effective method for selecting the parameters of the FMCW waveform and for jointly calibrating the radar system with a depth sensor. Finally, we demonstrate that our system guarantees reliable and robust performance.

Data fusion of radar and stereo vision for detection and tracking of moving objects

“…It is desired to extract phase differences for the particular bins in the CRDM whose energies exceed the local interference. To do so, the method implemented by Molchanov et al [69] is used, which calculates bin phase differences from the CRDMs of the two receive channels. The resulting angle for the bin (i, j) is given by 20) where ∠CRDM IFn i,j is the phase of bin (i, j) of the n th receive IF channel.…”

Sparsity-based dynamic hand gesture recognition using micro-Doppler signatures

“…In [3], a portable radar sensor is employed to recognize dynamic hand gestures by using application-specific features and principal component analysis (PCA), and the results illustrate the potential of radar-based dynamic hand gesture recognition for smart home applications. The authors of [4,5] model human hand as a non-rigid object and use a frequency modulated continuous wave (FMCW) radar to obtain the range-Doppler images of dynamic hand gestures of drivers' gestures. As presented in [5], radar echoes of dynamic hand gestures contain multiple components with time-varying frequency modulations, which are referred to as micro-Doppler signatures in radar jargon [6][7].…”

“…The authors of [4,5] model human hand as a non-rigid object and use a frequency modulated continuous wave (FMCW) radar to obtain the range-Doppler images of dynamic hand gestures of drivers' gestures. As presented in [5], radar echoes of dynamic hand gestures contain multiple components with time-varying frequency modulations, which are referred to as micro-Doppler signatures in radar jargon [6][7]. Micro-Doppler effect has been widely used for human activity classification [7][8][9][10][11], but microDoppler-based methods for hand gesture recognition have not been sufficiently investigated yet [5].…”

Dynamic hand gesture classification based on radar micro-Doppler signatures

“…Compared to video-based methods, the radar micro-Doppler analysis is all-weather and unaffected by natural light conditions and, therefore, is worth investigating for robust HCI systems. There has been some literature on dynamic hand gesture using radar sensors [11]- [12]. Features are extracted from the Doppler shift images, then a K-Nearest Neighbor (KNN) classification approach is used to classify four gestures in [11].…”

“…Features are extracted from the Doppler shift images, then a K-Nearest Neighbor (KNN) classification approach is used to classify four gestures in [11]. In [12], the authors extract features from the range-Doppler map.…”