Search

Multipolarizations of micro-Doppler signature (MDS) were combined to classify the elevation angle of a drone by a convolutional neural network (CNN). We classified the drone's elevation angle based on the MDS, which depends on the elevation angle of the drone. To enhance the classification accuracy, we utilized micro-Doppler from multiple polarized radar signals. We utilized and analyzed four different polarizations for the receiver, namely, vertical/horizontal/right-handed circular polarization (RHCP)/left-handed circular polarization (LHCP), while the polarization for the transmitter was vertical. The four receivers with different polarizations were fully synchronized with Tx for accurate MDS measurement for each polarization. The radar data received from the multiple polarizations were combined for the classification algorithm based on CNN. The classification rate of the elevation angles of a drone was improved from 84.745% to 97.9% compared to a single polarization by using multiple polarizations.

We propose a drone classification method for polarimetric radar, based on convolutional neural network (CNN) and image processing methods. The proposed method improves drone classification accuracy when the micro-Doppler signature is very weak by the aspect angle. To utilize received polarimetric signal, we propose a novel image structure for three-channel image classification CNN. To reduce the size of data from four different polarization while securing high classification accuracy, an image processing method and structure are introduced. The data set is prepared for a three type of drone, with a polarimetric Ku-band frequency modulated continuous wave (FMCW) radar system. Proposed method is tested and verified in an anechoic chamber environment for fast evaluation. A famous CNN structure, GoogLeNet, is used to evaluate the effect of the proposed radar preprocessing. The result showed that the proposed method improved the accuracy from 89.9% to 99.8%, compared with single polarized micro-Doppler image. We compared the result from the proposed method with conventional polarimetric radar image structure and achieved similar accuracy while having half of full polarimetric data.

In this letter, we propose a method of monitoring driver's movement using a small-sized millimeter-wave radar sensor. First, we install a frequency-modulated continuous wave radar sensor on the steering wheel and collect reflected signals for various driver motions. Because the reflection patterns are different for each motion, we can distinguish different movements of the driver by analyzing the received signal. In our method, we use the spectrogram of the received signal obtained through multiple measurements and apply a window function to extract the radar signal in the form of an image. Then, we use the convolutional neural network architecture to classify the radar signal images. The classification results show that our proposed method can classify four different movements of the driver with an accuracy higher than 80%.

In this paper, we propose a method to classify the human and vehicle objects by combining a support vector machine (SVM) and the deep learning model, you only look once (YOLO), in a high-resolution automotive radar system. To enhance the classification performance, the boundaries of targets estimated from the YOLO model are delivered to the SVM. Then, the overall classification accuracy can be improved by combining the results from the YOLO and SVM with predefined target boundaries. The results show that the proposed method has a better classification performance than those obtained using only YOLO or SVM. From the actual measurements, the proposed method can classify humans and vehicles over 90% accuracy in high-resolution automotive radar.

This paper proposes a method to simultaneously detect and classify objects by using a deep learning model, specifically you only look once (YOLO), with pre-processed automotive radar signals. In conventional methods, the detection and classification in automotive radar systems are conducted in two successive stages, however, in the proposed method, the two stages are combined into one. To verify the effectiveness of the proposed method, we applied it to the actual radar data measured using our automotive radar sensor. According to the results, our proposed method can simultaneously detect targets and classify them with over 90% accuracy. In addition, it shows better performance in terms of detection and classification, compared with conventional methods such as density-based spatial clustering of applications with noise or the support vector machine. Moreover, the proposed method especially exhibits better performance when detecting and classifying a vehicle with a long body.

This paper presents a pulse radar system to detect drones based on a target fluctuation model, specifically the Swerling target model. Because drones are small atypical objects and are mainly composed of non‐conducting materials, their radar cross‐section value is low and fluctuating. Therefore, determining the target fluctuation model and applying a proper integration method are important. The proposed system is herein experimentally verified and the results are discussed. A prototype design of the pulse radar system is based on radar equations. It adopts three different pulse modes and a coherent pulse integration to ensure a high signal‐to‐noise ratio. Outdoor measurements are performed with a prototype radar system to detect Doppler frequencies from both the drone frame and blades. The results indicate that the drone frame and blades are detected within an instrumental maximum range. Additionally, the results show that the drone's frame and blades are close to the Swerling 3 and 4 target models, respectively. By the analysis of the Swerling target models, proper integration methods for detecting drones are verified and can thus contribute to increasing in detectability.

We present a polarimetric analysis of small drones from different aspect angles. Polarimetric analysis can provide more information of a target, since the returned radar signal is affected by different wave polarization. The analysis is performed with micro-Doppler signature (MDS) to investigate micromotions of the drone detected by the radar. We measured operating small drones in an anechoic chamber from two aspect angles, 0° and 90°. An outdoor experiment was carried out with metal clutters for verification in real environment. The indoor analysis result shows that copolarized antenna receives signals better than cross polarized when the aspect angle is 0°, and vice versa. We also verified that cross-polarized antenna receives MDS from the drone better than copolarized antenna, from outdoors when an aspect angle is almost 90°. By utilizing the polarimetric characteristic of the drone at this frequency band, it is preferable to use a polarimetric radar for drone detection.

This paper presents a super-fast radar map generation based on newly proposed compressed Iterative Adaptive Approach (IAA) method. The proposed method consists of matrix compression and revised steering angle adaptation method. The experiment results show that the proposed method greatly improves the computational efficiency without map resolution degradation.

In this paper, we demonstrated the feasibility of the Aerosol Deposition (AD) method which can be adapted as a future fabrication process for flexible electronic devices. On the basis of this method’s noticeable advantages such as room-temperature processing, suitability for mass production, wide material selectivity, and direct fabrication on a flexible substrate, we fabricated and evaluated a flexible conductive bridge random access memory (CBRAM) to confirm the feasibility of this method. The CBRAM was fabricated by the AD-method, and a novel film formation mechanism was observed and analyzed. Considering that the analyzed film formation mechanism is notably different with previously reported for film formation mechanisms of the AD method, these results of study will provide strong guidance for the fabrication of flexible electronic device on ductile substrate.

Electromagnetic wave characteristic of slot antenna at rectangular waveguide is discussed in this study. The rectangular waveguide is attached to infinite ground plane, and on the ground plane, one layer of coating exist. Material of coating layer is assumed that has arbitrary permeability, permittivity, thickness, and loss tangent. The aperture field distributions, far-field radiation patterns are extracted from electromagnetic field analysis. To analyze the electromagnetic field, the theory of continuity of the magnetic field is forced boundary condition from the waveguide, through coating layer, to free-space. By forcing boundary equations, the spatial domain and spectrum domain Green's function for internal and external are derived. By based on Green's functions, integral equations are obtained and these integrals are solved by using numerical methods. After solving the equations, the field components are obtained. Aperture electromagnetic field and far-field radiation pattern of the waveguide slot antenna are available using the method of stationary phase.

A 79-GHz frequency modulated continuous wave (FMCW) radar prototype for use in autonomous vehicles (Level-4), and its basic performance was evaluated. The system comprised 12 Tx and 16 Rx multiple-input-multiple-output (MIMO) antennas with high resolution in both the horizontal and vertical directions. The system was loaded on the vehicle, and the main functions, such as detection, tracking, and classification, were assessed via a road driving test. Furthermore, a grid map radar image was implemented to image a parked vehicle next to the road.