In this paper, a real-time signal processing framework based on a 60 GHz frequency-modulated continuous wave (FMCW) radar system to recognize gestures is proposed. In order to improve the robustness of the radar-based gesture recognition system, the proposed framework extracts a comprehensive hand profile, including range, Doppler, azimuth and elevation, over multiple measurement-cycles and encodes them into a feature cube. Rather than feeding the range-Doppler spectrum sequence into a deep convolutional neural network (CNN) connected with recurrent neural networks, the proposed framework takes the aforementioned feature cube as input of a shallow CNN for gesture recognition to reduce the computational complexity. In addition, we develop a hand activity detection (HAD) algorithm to automatize the detection of gestures in real-time case. The proposed HAD can capture the time-stamp at which a gesture finishes and feeds the hand profile of all the relevant measurementcycles before this time-stamp into the CNN with low latency. Since the proposed framework is able to detect and classify gestures at limited computational cost, it could be deployed in an edge-computing platform for real-time applications, whose performance is notedly inferior to a state-of-the-art personal computer. The experimental results show that the proposed framework has the capability of classifying 12 gestures in realtime with a high F1-score.

This paper deals with several original contributions to an automatic target recognition (ATR) system, which is applied to underwater mine classification. The contributions concentrate on feature selection and object classification. First, a sophisticated filter method is designed for the feature selection. This filter method utilizes a novel feature relevance measure, the composite relevance measure (CRM). Feature relevance measures in the literature (e.g., mutual information and relief weight) evaluate the features only with respect to certain aspects. The CRM is a combination of several measures so that it is able to provide a more comprehensive assessment of the features. Both linear and nonlinear combinations of these measures are taken into account. A wide range of classifiers is able to provide satisfactory classification results by using the features selected according to the CRM. Second, in the step of object classification, an ensemble learning scheme in the framework of the Dempster–Shafer theory is introduced to fuse the results obtained by different classifiers. This fusion can improve the classification performance. We propose a reasonable construction of the basic belief assignment (BBA). The BBA considers both the reliability of the classifiers and the support of individual classifiers provided to the hypotheses about the types of test objects. Finally, this ATR system is applied to real synthetic aperture sonar imagery to evaluate its performance.

This paper deals with gesture recognition using a 77 GHz FMCW radar system based on the micro-Doppler (μ D) signatures. In addition to the Doppler information, the range information is also available in the FMCW radar. Therefore, it is utilized to filter out the irrelevant targets. We have proposed five micro-Doppler based handcrafted features for gesture recognition. Finally, a simple k-nearest neighbor (k-NN) classifier is applied to evaluate the importance of the five features. The classification results demonstrate that the proposed features can guarantee a promising recognition accuracy.

In this paper, a region-based deep convolutional neural network (R-DCNN) is proposed to detect and classify gestures measured by a frequency-modulated continuous wave radar system. Micro-Doppler (μD) signatures of gestures are exploited, and the resulting spectrograms are fed into a neural network. We are the first to use the R-DCNN for radar-based gesture recognition, such that multiple gestures could be automatically detected and classified without manually clipping the data streams according to each hand movement in advance. Further, along with the μD signatures, we incorporate phase-difference information of received signals from an L-shaped antenna array to enhance the classification accuracy. Finally, the classification results show that the proposed network trained with spectrogram and phase-difference information can guarantee a promising performance for nine gestures.

In this paper, a signal processing framework using high-resolution algorithms is applied to automotive radar systems for target separation purposes. In many critical use cases, targets sharing similar parameters, i.e., range and relative velocity, can hardly be discriminated in a 2-dimensional (2-D) range-Doppler spectrum via conventional radar signal processing techniques. The proposed framework by taking advantage of a 2-D model-based algorithm with high-resolution capability, i.e., modified matrix enhancement and matrix pencil (MMEMP), is able to separate the overlapping targets by jointly estimating their aforementioned target parameters in a precise manner. Additionally, to reduce computational cost, the presented framework could preselect the peaks (local maxima) of interest via a 2-D model order selection algorithm, i.e., 2-D subspace-based automatic model order selection (2-D SAMOS), and apply the MMEMP only in multi-target situations. Finally, simulation and experiments are carried out to evaluate the performance of the proposed high-resolution target separation framework.

This paper provides a concise yet comprehensive review of spatial environment sensing and perception in automated systems, crucial for intelligent applications such as smart cities, smart homes, navigation, automated driving and industry 4.0. With a focus on achieving dependable performance even in harsh environments and enabling affordable mass deployment, the review explores sensor technologies, calibration, diagnostics, performance degradation analysis, and machine-learning-based perception algorithms. Our contributions aim to deepen understanding and drive progress in automated systems, addressing challenges across diverse application scenarios. Through a meticulous analysis of the pros and cons of state-of-the-art technologies, the paper sheds light on future trends in research and development. This work serves as a valuable resource for researchers, practitioners, and industry professionals seeking insights into the evolving landscape of spatial environment sensing and perception.