Search

A multisensor data fusion algorithm is proposed in this study for life detection in cluttered environments. The method consists of four steps: data acquisition, data preprocessing, data fusion, and result sort. First, four kinds of data (RGB image, RGB video, infrared image, and radar wave) are acquired from three different sensors (RGB camera, infrared camera, and life detection radar). Then, four specified algorithms are used on each data for data preprocessing. Third, an ordered weighted average (OWA)-based data fusion is used to fuse the four single results. The result is a sort of four possible results ($\textit {Alive}$ , $\textit {Dead}$ , $\textit {Animal}$ , and $\textit {None}$). A series of cluttered environments are designed to verify the effectiveness of the proposed method. The results show that the data fusion method can effectively improve the success rate of life detection in cluttered environments. Specifically, the average accuracies of 97.8%, 96.7%, and 89.7% under different distances, light intensities, and shelter, respectively, are obtained. [ABSTRACT FROM AUTHOR]

Radar-based dynamic hand gesture classification has been an active research field in recent years. Deep learning methods using radar sensors are widely used to classify dynamic hand gestures. The existing deep learning methods need the overhead of performing the slow- and fast-time Fourier transforms to obtain the various spectrum images as the input of the deep convolutional neural network (DCNN). In this article, a dynamic hand gesture classification method based on the multichannel radar using a multistream fusion 1-D convolutional neural network (MSF-1-D-CNN) is proposed. The proposed MSF-1-D-CNN has four branches in parallel, and each branch has the inception modules to extract features from the raw echo data of each receiving antenna. Then, the extracted features from each branch are concatenated, and the long short-term memory (LSTM) layer is utilized to extract the temporal characteristic of the concatenated features. Finally, the dense layer with the softmax function is utilized to obtain the classification result of hand gestures. The experimental results show that, compared with existing methods, the proposed method using multichannel radar data can provide improved classification accuracy when the hand has a large incident angle and distance from the radar. Moreover, the proposed method can also reduce the network parameters and computational complexity, which has the potential to be implemented on commercial embedded systems. [ABSTRACT FROM AUTHOR]

The ambiguity problem of targets in Doppler beam sharpening (DBS) with forward-looking radar is considered. While DBS is proposed earlier to improve the angular resolution of the radar while keeping the antenna aperture size limited, such a solution suffers from ambiguities in the case of targets positioned symmetrically with respect to the platform movement. To address this problem, an approach named unambiguous Doppler-based forward-looking multiple-input multiple-output (MIMO) radar beam sharpening scan (UDFMBSC) is proposed, based on the combination of MIMO processing and DBS. The performance of the proposed method is compared to existing approaches using simulated data with point-like and extended targets. The method is successfully verified using experimental data. [ABSTRACT FROM AUTHOR]

A ${k}$ -space and Doppler velocity decomposition based on an accurate millimeter wave (mmW) 3-D target localization method is presented, using the range points’ migration (RPM) method to provide multi-information associated with point clouds. The incoherent method, known as RPM, has a number of advantages over coherent localization, including avoiding a false response due to phase uncertainty or the necessity for highly accurate phase calibration in multiple arrays. However, various concerns must be addressed to retain the benefit of high-frequency mmW radar. In order to bring some benefits of high-frequency mmW radar into RPM scheme, this study introduces the ${k}$ -space and Doppler velocity decomposition schemes for multiple objects moving at different speeds into the RPM scheme, where a new weighted term is introduced. In addition, the RPM point cloud is incorporated with the incoherent Doppler velocity estimation method known as the weighted kernel density (WKD) method, which provides a multifunctional 3-D localization. The mmW radar experiment in the 79-GHz band demonstrates that our proposed method achieves accurate 3-D Doppler-associated localization, even with a small aperture array. [ABSTRACT FROM AUTHOR]

Dynamic identification is crucial for space target investigation and awareness, which is especially challenging for uncooperative and uncontrolled targets. This article presents a dynamic identification algorithm using the time-variant geometric feature flow extracted from an inverse synthetic aperture radar (ISAR) image sequence. The range-Doppler (RD) projection, along with the sequential radar light of slight of the target component, intrinsically relies on the targets’ dynamic states. With the accommodation of a long short-time memory (LSTM) network, reliable dynamic identification of space targets can be implemented by exploiting the geometrical feature flow from the ISAR sequence. The superiority of the proposed method is demonstrated through comparison experiments. [ABSTRACT FROM AUTHOR]

The respiratory rate (RR) and waveform play an important role in reflecting health conditions. Some diseases such as Biot’s breathing and Chyne–Stokes respiration require long-term continuous respiration monitoring, which is normally conducted by hospitals or sleep centers. Portable sensor devices, such as piezoelectric sensors, watch-type monitoring devices, ultrasound technologies, radar sensors, and so on, are required to help patients that are difficult to attend to such settings. In terms of these choices, the radar sensor can provide a more comfortable and contactless experience. Most of the existing methods analyze the 1-D radar signal. The 2-D radar signal, such as the radar image, contains more spatial information that is easier to be interfaced with further pose or gesture recognition functions to extract useful information. This article presents an image processing approach with radar images generated from an ultrawideband (UWB) radar sensor to produce respiration waveforms and estimate RR in real-time. The raw signals from the radar sensor are converted to a 2-D heatmap image, and then an image-processing algorithm is employed to extract respiration information including the respiration waveform from the heatmap. Experimental results show that the proposed system can reliably measure respiration motion in static situations such as lying in the supine or lateral position with an average precision of 95.02%. [ABSTRACT FROM AUTHOR]

Complex approximate message passing (CAMP) algorithm is a promising compressed sensing (CS) method for inverse synthetic aperture radar (ISAR) imaging with the merits of fast convergence and good reconstruction. To improve the imaging performance and accelerate the convergence, a new strategy weighted CAMP based ISAR imaging method has been proposed. Rather than solving a sequence of weighted ${l}_{{1}}$ minimization problems, the weighted CAMP problem is solved directly by using a new weighted threshold, which not only ensures the convergence of the algorithm but also improves the convergence speed. To accelerate the convergence furtherly, a new point is chosen smartly in the scalar threshold function, which borrows the idea of fast iterative shrinkage-thresholding algorithm (FISTA). As weighting adaptively to the signal and the noise is more appropriate to maintain the target information and suppress the noise, random forests (RF) algorithm is employed to classify the signal and the noise, and strategy weighting is used based on the classification result. The proposed algorithm was applied into complex sinusoids, quasi-real, and real ISAR data. It has got the best imaging result among the algorithms of CAMP class and need less imaging time than CAMP and weighted CAMP (WCAMP). Therefore, the proposed algorithm is an efficient ISAR imaging method with good performance. [ABSTRACT FROM AUTHOR]

Accurate Burden Surface Profile (BSP) detection is important for the operation of Blast Furnace (BF). The signal-to-noise ratio of radar signals changes greatly during both the charging period of BF and the long maintenance period of the radar device, which increases the difficulty of radar BSP detection. The traditional radar BSP detection method based on signal energy relies on manually selected detection thresholds according to the noise intensity. Hence, the accuracy of the traditional radar BSP detection method is not reliable in the long term. To address this problem, we propose a novel learning-based Key Points estimation (KP-BSP) method to detect the key points of radar reconstructed BSP image, and a new Key Points-based Connected Region Noise Reduction (KP-CRNR) algorithm to remove the noise-affected regions. The prediction deviation at detected key points (at the positions of the mechanical probes) is then used to correct the radar detection results, leading to the improvement of radar detection accuracy. The experimental data were collected from Wuhan Iron Steel Company No.7 BF. The results show that the proposed methods can achieve an average RMSE of 0.0156m, which is improved by more than 50% compared with previous methods. The long-term reliability of the proposed method is also demonstrated in this dataset. [ABSTRACT FROM AUTHOR]

In the view of national security, radar micro-Doppler (m-D) signatures-based recognition of suspicious human activities becomes significant. In connection to this, early detection and warning of terrorist activities at the country borders, protected/secured/guarded places and civilian violent protests is mandatory. Designing an automated human suspicious activities: army crawling, army jogging, jumping with holding a gun, army marching, boxing, and stone-pelting/grenades-throwing, recognition system using a suitable deep convolutional neural network (DCNN) model is rapidly growing due to its inherent in-depth features extraction capability. As a value addition to this research, an X-band continuous wave (CW) 10 GHz radar has been developed at our radar systems laboratory and used to acquire the m-D signatures, to prepare a dataset (DIAT- $\mu $ RadHAR) corresponding to above mentioned suspicious activities. In order to prepare a realistic dataset, human targets of different heights, weights, and gender are directed to perform the suspicious activities in front of the radar at different ranges between 10 m - 0.5 km and at different target aspect angles (0°, ±15°, ±30° and ±45°). A lightweight DCNN architecture ($\mu $ RadNet) is also designed and trained with the prepared DIAT- $\mu $ RadHAR dataset comprising 3780 samples. The performance and recognition accuracy of $\mu $ RadNet is statistically computed, and the results are compared to the state-of-the-art (SOTA) CNN models. The $\mu $ RadNet DCNN model outperforms the SOTA CNN models, giving 99.22% of overall classification accuracy, 0.09M parameters, and 0.40G floating point operations (FLOPs) with minimal false negative/positive rates. The time-complexity of the designed lightweight $\mu $ RadNet DCNN model is 0.12 s, which evidences the suitability of our DCNN model for the on-device implementation. [ABSTRACT FROM AUTHOR]

The presence of rain can negatively affect the performance of many sensors such as X-band radar. In this paper, an effective approach is proposed to mitigate the effect of rain on significant wave height (${H}_{s}$) estimation from X-band radar sensor data along with a machine-learning (ML)-based method. First of all, the haze removal algorithm is applied to rain-contaminated radar images as pre-processing. Then, three different features are extracted from the processed radar images. Different combinations of these three features are utilized to estimate ${H}_{s}$ under the rain condition by using support vector regression (SVR)-based and temporal convolutional network (TCN)-based regression methods. It is found that the root-mean-square-errors (RMSEs) of ${H}_{s}$ estimation results using two typical methods (signal-to-noise ratio (SNR)-based and ensemble empirical mode decomposition (EEMD)-based linear fitting methods) are decreased by 0.14 m and 0.48 m after introducing the haze removal algorithm, respectively. Also, a relatively high accuracy can be achieved using the SVR-based regression method with the combination of SNR and gray level co-occurrence matrix (GLCM) features. Compared to the SNR-based and EEMD-based linear regression methods, the proposed SVR-based method further improves the estimation accuracy, with reductions of RMSE by 0.19 m and 0.82 m, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we aim at proposing an efficient inverse synthetic aperture radar (ISAR) imaging method for multiple moving targets in the framework of alternating direction method of multipliers (ADMM). Firstly, the motion phase errors of the moving targets are estimated via the fractional Fourier transform (FrFT) operation. After that, the hybrid ADMM (Hy-ADMM) which incorporates the regularization terms of $\ell _{1}$ norm and total-variation (TV) of the image magnitude is presented to recover the images. The Hy-ADMM reconstruction would lead to a sub-image set corresponding to the number of moving objects, since the phase errors compensated echoes are separately obtained for different moving targets by the FrFT estimated phase factors. As a result, a maximum and minimum generalized likelihood ratio test (mm-GLRT) based composite imaging technique is utilized to obtain a whole imaging result from the compensated image sets. Compared with traditional imaging methods, the proposed scheme obtains better performance in terms of suppressing the noise and preserving the target features. Finally, numerical experiments are applied to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Non-line-of-sight (NLOS) detection is widely encountered in military and civilian fields, such as urban battles and disaster rescues. In this study, a novel multipath imaging approach is proposed to solve the problem of multi-target localization behind an L-shaped corner for a single-channel ultra-wide-band (UWB) radar. Specifically, a multipath propagation model based on an L-shaped corner is established, and the positions of virtual radars are analyzed by the specular reflection feature of electromagnetic wave, which forms a virtual array aperture to achieve enough image resolution. Then, the radar echo is mapped based on each propagation path to form multiple images. Finally, according to the trajectory distribution in each image, the incoherent addition is exploited to fuse the multiple images to focus on the target locations. Simulation and experimental results demonstrate that the estimated target positions are consistent with the actual target locations, and the proposed multipath imaging algorithm is applicable in the case of partial path loss. [ABSTRACT FROM AUTHOR]

Among various types of sensors, through-the-wall imaging radar (TWIR) is widely used in concealed targets detection and urban environment perception. Especially, multi-view TWIR has been received more and more attention in recent years for its ability to provide more accurate position estimation and reduce the blind areas. However, when exploiting the multi-view TWIR to detect targets in the complicated indoor environment with an unavailable global positioning system, the relative position of the radars is hard to be obtained and the acquired non-uniform images cannot be aligned automatically. To deal with these problems, an image registration approach based on graph matching for multi-view TWIR is proposed in this paper. In this approach, we exploit an important feature of multi-view TWIR images: the invariant relative position of targets in different views. Based on this characteristic, the acquired images are modeled as complete graphs, and graph matching is employed to acquire the relative position parameters of the radars and register the images. Compared with the classic method, the proposed method can overcome the critical challenges of invalid local features as well as high-intensity ghosts, and achieve better performance for multi-view TWIR image registration. The effectiveness of the proposed method is evaluated via both simulations and real data tests. [ABSTRACT FROM AUTHOR]

Millimetre-wave (mmWave) radar is increasing in popularity for human activity recognition, due to its advantages of high resolution, non-intrusive nature and suitability for various environments. In this paper, we present a novel human posture estimation system using mmWave radars. The system detects people with arbitrary postures in indoor environments at close distances (within two metres), and estimates the posture by localising the key joints. We use two mmWave radars to capture the scene and a neural network model to estimate the posture. The neural network model consists of a part detector that estimates the subject’s joint positions, and a spatial model that learns the correlation between the joints. A temporal correlation step is introduced to further refine the estimate when in real-time operation. The system can provide an accurate posture estimate of the person in real-time at 20 fps, with a mean localisation error of 12.2 cm and an average precision of 71.3%. [ABSTRACT FROM AUTHOR]

Using wideband signals to improve the resolution performance of forward-looking imaging radar sensors is a very valuable topic. However, the frequency point and angle information are coupled in the array manifold for the wideband array signal, making the high-resolution estimation of range and angle extremely difficult under low complexity. In this paper, we propose a novel algorithm for the wideband forward-looking imaging radar. Firstly, the time delays are estimated by the estimation of signal parameters via rotation invariance techniques (ESPRIT). Then, multiple sets of filters are constructed by using the estimated delays and frequency information. The filters are equipped with sliding window technology to tackle the angle-frequency coupling problem encountered by wideband radar. Through these filters, the received signals are divided into several clusters that correspond to different time delays. Next, the relaxation (RELAX) algorithm is used to estimate the angle of the wideband signal in each cluster. Finally, the range refinement is carried out by using data from all antennas. Compared with the existing algorithms, the proposed Hybrid ESPRIT and RELAX algorithm with clustEring (HERE) decouples the frequency point and angle information for wideband forward-looking imaging radar and then achieves better imaging performance. A series of numerical experiments, including simulation experiments and actual data collected from a wideband forward-looking imaging prototype, have verified the superiority of the algorithm. [ABSTRACT FROM AUTHOR]

This study proposes a data fusion method for multiradar systems to enable measurement of the respiration of multiple people located at arbitrary positions. Using the proposed method, the individual respiration rates of multiple people can be measured, even when echoes from some of these people cannot be received by one of the radar systems because of shadowing. In addition, the proposed method does not require information about the positions and orientations of the radar systems used because the method can estimate the layout of these radar systems by identifying multiple human targets that can be measured from different angles using multiple radar systems. When a single target person can be measured using multiple radar systems simultaneously, the proposed method selects an accurate signal from among the multiple signals based on the spectral characteristics. To verify the effectiveness of the proposed method, we performed experiments based on two scenarios with different layouts that involved seven participants and two radar systems. Through these experiments, the proposed method was demonstrated to be capable of measuring the respiration of all seven people by overcoming the shadowing issue. In the two scenarios, the average errors of the proposed method in estimating the respiration rates were 0.33 and 1.24 respirations per minute (rpm), respectively, thus demonstrating accurate and simultaneous respiratory measurements of multiple people using the multiradar system. [ABSTRACT FROM AUTHOR]

Microwave photonic (MWP) radar has the advantages of generating and processing wide bandwidth microwave signals, reconfigurability, high immunity to electromagnetic interference compared to microwave electronic radar. It has the potential to be used in applications such as intelligent autonomous and cyber-physical systems. Recent advances in microwave photonic technology led to the generation, fast processing, and control of broadband signals. Because of the advancements in photonic technologies, next-generation microwave photonic radar is becoming more prominent. This article reviews the most recent advancements and future directions in MWP radars. This review article overviews the different components of microwave photonic radar, different design challenges, and issues pertaining to it. We present a comparative study of different MWP radars on different applications. It also discusses possible future research directions of MWP radar. [ABSTRACT FROM AUTHOR]

Millimeter-wave and microwave short-range radar are among the most promising environmental sensing methods, with applications to situations that are otherwise optically invisible. This paper presents a Doppler velocity-enhanced range migration algorithm (RMA) that achieves both high spatial resolution and low-complexity three-dimensional (3-D) radar imaging. In this method, we address the problem of human body recognition with motion using the assumption that the motion of different human parts generates distinct micro-Doppler variations in the radar data. These variations could not only separate the RMA images with different Doppler velocities in a coherent integration-based radar imaging process, but enhances a noise reduction effect by decomposing in the Doppler velocity space. To achieve a low complexity in 3-D imaging, we incorporate the RMA method and Doppler velocity-based data decomposition. The results of numerical and experimental tests on a realistic human phantom with a walking motion demonstrate that our method provides more informative and highly separated 3-D images, even in much low SNR situation. [ABSTRACT FROM AUTHOR]

Reasonable and effective resource allocation strategy can fully utilize the system potential of the radar sensor network especially under the limited resources. In this paper, a joint time and aperture resource allocation optimization problem of multi-target inverse synthetic aperture radar (ISAR) imaging in phased-array radar sensor network with game theory is investigated. The purpose of the resource allocation optimization problem is to complete the whole imaging tasks with high resolution within limited time and aperture resources. Obviously, the competition for radar resources exists among the targets under resource constraints. After analyzing the relationship between image resolution and time and aperture resources, the resource allocation optimization problem which is also a distributed decision problem is established and turns out to be an exact potential game. Thereafter the optimal resource allocation strategy is obtained by finding a Nash equilibrium (NE) strategy with an improved best response dynamic (IBSD) algorithm. Numerical experiments show the effectiveness of the proposed algorithm which can obtain a satisfied resource strategy profile. [ABSTRACT FROM AUTHOR]

The development of an automotive surface recognition system is an important and yet unsolved task. In the current study we are considering a novel approach to surface classification based on the analysis of the real road surface images obtained using the 79 GHz imaging radar and demonstrate the advantage of millimeter wave radar for surface discrimination for automotive sensing. The proposed experimental technique in combination with a convolutional neural network provides high surface classification accuracy. [ABSTRACT FROM AUTHOR]

Terahertz (THz) radar imaging has widely adopted for security screening of standoff human body in recent years, owing to its capacities of high resolution, harmless, contactless, and penetrate clothing. However, THz radar security screening for walking human is still a challenge due to the non-rigid motion of walking. To figure it out, a THz radar security screening method for walking human torso is proposed with multi-angle synthetic aperture. In this method, the echo data of walking human torso component is assumed as a rigid motion model within a short time. Particularly, the torso component has the maximum ratio of surface area and echo energy, which means that its motion phase error can be detected after fractional Fourier transform processing. Besides, after the correction and imaging processing, the imaging results under different angles are fused by coherent integration with registration processing to improve the integrity of scattering information, which is incomplete within a short aperture due to self-occlusion and the changes in incident angles. The simulation experiments are conducted to verify the imaging quality and feasibility of the proposed method. Moreover, the real small aperture echo data of moving torso collected by our THz radar (that operates at 330GHz with the bandwidth of 30GHz and the output peak power of 5mW) is processed via the proposed method to indicate the significance of multi-angle imaging. [ABSTRACT FROM AUTHOR]

Human Machine Interaction based on air gestures finds an increasing number of applications in consumer electronics. The availability of mmWave technology, combined with machine learning, allows the detection and classification of gestures, avoiding high-resolution LIDAR or video sensors. Nevertheless, in most of the existing studies, the processing takes place offline, takes into account only the velocity and distance of the moving arm, and can handle only gestures that are conducted very close to the sensor device, which limits the range of possible applications. Here, we use an experimental multi-channel mmWave-based system that can detect small targets, like a moving arm, up to a few meters away from the sensor. As our pipeline can estimate and take into account the angle of arrival in azimuth and elevation, it has the ability to classify a greater variety of dynamic gestures. Furthermore, the digital signal processing chain we present here, runs in real-time, incorporating an event detector. Whenever an event is detected, a novel empirical feature extraction takes place and a Multi-Layer Perceptron is deployed to infer the type of the gesture. To evaluate our setup and signal processing pipeline, a dataset with ten subjects, performing nine gestures was recorded. Our method yielded 94.3% accuracy on the test set, indicating a successful combination of our proposed sensor and signal processing pipeline for real time applications. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel people counting algorithm exploiting convolutional neural network (CNN) using a low radiation impulse radio ultra-wide bandwidth (IR-UWB) radar. Because of the ever-changing signals caused by the various cases of human motion scales, superposition and obstruction of signals as well as the attenuate of signal’s strength along the distance and the angle, it is not easy to handle the people counting task by directly detecting targets for each range bin. Thus, we hope to excavate the information of targets’ patterns, including their densities and forms of patterns’ distributions in the detecting region to execute the counting task. To achieve this, the multi-scale range-time maps are extracted from the received data and further used to classify the number of people using the CNN. Finally, the experiments are conducted to show the priority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Millimeter-wave (MMW) imaging radar is one of the major environmental sensors in recent self-driving or driver assistance systems and provides environmentally robust sensing even in optically challenging conditions. As a promising three-dimensional (3-D) radar imaging technique, this study focuses on the range points migration (RPM) method, which has advantages in terms of accuracy and low complexity. In the original RPM algorithm, the parameters are manually or empirically determined by considering the sensor configuration and target shape or distance. To address this limitation, we introduced a novel parameter optimization scheme based on the Gaussian mixture model (GMM) and the expectation maximization (EM) algorithm. In addition, we used the k-space decomposition-based parameter determination scheme to determine target shape-dependent parameter selection. The results, assuming the human body imaging scenario, showed that our proposed method retains a highly accurate target image without requiring empirical parameter selection. [ABSTRACT FROM AUTHOR]

Through-wall mapping is an emerging field of research with promising applications varying from search and rescue, to health care and to security. Radar is a valuable tool in this process, mainly due to its long wavelength, which can pass through construction materials. However, this capability comes at a price, namely multipath reflections caused by the environment, which can reduce the usability of the produced map considerably. This paper proposes methods to detect and isolate these multipath reflections, eventually leaving out a usable map of the enclosed environment. For this purpose, two different radars, one operating at 24GHz and the other at 76GHz, were evaluated in various wall configurations constructed inside an enclosed space using portable wall segments. The testing arena was probed from the outside with the radars mounted on the top of a differential drive mobile robot. The paper shows that the proposed methods are effective in eliminating multipath reflections and in building an accurate representation of the environment using the radars. [ABSTRACT FROM AUTHOR]

Obtaining the accurate and real-time state of surrounding objects is essential for automated vehicle planning and decision-making to ensure safe driving. In complex traffic scenarios, object occlusion, clutter interference, and limited sensor detection capabilities lead to false alarms and missed object detection, making it challenging to ensure the stability of tracking and state prediction. To address these challenges, in this study, we developed a robust multi-object detection and tracking method for moving objects based on radar and camera data fusion. First, the radar and camera perform target detection independently, and the detection results are correlated in the image plane to generate a random finite set with an object type. Then, based on the Gaussian mixture probability hypothesis density algorithm framework, the tracking process is improved using elliptic discriminant thresholds, an attenuation function, and simplified pruning methods. The experimental results demonstrate that the improved algorithm can accurately estimate the number and state of targets in object occlusion, measurement loss scenarios, and achieve robust continuous multi-object tracking. The proposed method could guide the design of safer and more efficient intelligent driving systems. [ABSTRACT FROM AUTHOR]

Due to the influence of the complex marine environment, the marine target detection based on statistical theory is difficult to achieve high-performance. Moreover, due to various targets’ motion characteristics, only using a single feature for detection is unreliable. In this paper, from the perspective of feature extraction and classification, marine target and sea clutter are classified by deep learning methods. To achieve the required false alarm rate, the dual-channel convolutional neural networks (DCCNN) and false-alarm-controllable classifier (FACC)-based marine target detection method is proposed. Firstly, the measured sea clutter and the target signal are preprocessed to obtain the time-Doppler spectrum and amplitude information. The Marine-DCCNN (MDCCNN) is then constructed for features extraction and fusion, and the feature vectors of the signals are obtained. The performance of different feature extraction models is tested and compared. Finally, the FACC is used as a detector to classify the feature vectors into two categories and the control of the false alarm rate is realized. The detection performances were verified by two popular public radar datasets, i.e., IPIX radar dataset (floating target) and CSIR dataset (maneuvering marine target). The results show that compared with single-channel CNN and histogram of oriented gradient support vector machine (Hog-SVM) classification, a combination of MDCCNN feature extraction model and softmax classifier can achieve higher performance and controllable false alarm rate. Moreover, HH polarization and mixed training datasets under different sea states can help improve detection performance. [ABSTRACT FROM AUTHOR]

Inverse synthetic aperture radar (ISAR) imaging is an important technique for moving target identification and classification. For the space spinning targets, a long-time observation is required to estimate the spinning parameter in the conventional ISAR imaging methods. However, for the advanced multifunctional radar, which is used for multi-target surveillance, a long-time observation for only one target is the loss outweighs the gain. To decrease the observation time, we propose a novel imaging method for spinning space targets with short time observation in this paper. Firstly, we build the imaging model by using the azimuth rotation angle caused by the spinning motion rather than the translation motion to obtain the azimuth resolution. Secondly, we utilize the orthogonal coding signals with different delays to obtain enough equivalent pulses in the short observation time. Moreover, since the equivalent pulses are block-missing to avoid overlapping of the transmitting duration and the receiving duration, we transform the imaging problem to the compressed sensing (CS) problem and solve it by modifying the Smoothed L0-norm (SL0) algorithm. Finally, both the simulations and the experiments on real data are shown to demonstrate the validity of the proposed method. Since the observing time of the proposed method only needs to cover a small percentage of one spinning period, the proposed method can be used in multi-target surveillance such as satellites and space debris. [ABSTRACT FROM AUTHOR]

The development of safe intelligent transportation systems (ITS) has driven extensive research to come up with efficient environment perception techniques with a variety of sensors. In short range settings, Ultra Wide-Band (UWB) radars represent a promising technology for building reliable obstacle detection systems as they are robust to environmental conditions. However, UWB radars suffer from a segmentation challenge: localizing relevant regions of interest (ROIs) within its signals. This article proposes a segmentation approach to detect ROIs in an environment perception-dedicated UWB radar. Specifically, we implement a differential entropy analysis to detect ROIs. We evaluate our technique on a benchmark of more than 47 thousands samples. The obtained results show higher performance in terms of obstacle detection compared to state-of-the-art techniques, and a stable robustness even with low amplitude signals. [ABSTRACT FROM AUTHOR]

In radar networks, research on the task allocation strategy for multi-target imaging is essential, especially under limited radar resources. From the targets’ perspective, the goal is to acquire enough resources to obtain high-quality inverse synthetic aperture radar (ISAR) images. Then there is competition among targets for radar resources. Therefore, the task allocation optimization problem is considered as a cooperative game, specifically a non-transferable coalitional game when the sparse ISAR imaging algorithm is adopted. A stable coalition structure, which allows cooperation among targets to achieve satisfactory image resolution using the least amount of time, represents an optimal task allocation scheme. Then, the corresponding algorithm based on coalition-forming rules is proposed. Through the framework of cooperative game theory, a stable network structure (i.e., the task allocation strategy) is formed while minimizing the radar time resource cost. Finally, experiments confirm that the proposed algorithm can achieve an optimal task allocation strategy with a lower computation time cost. [ABSTRACT FROM AUTHOR]

Accurately capturing the burden surface information of a blast furnace (BF) is helpful to adjust the burden distribution matrix and improve the gas flow distribution, which is essential in the steel smelting industry. However, it is difficult to detect the burden surface because of the high temperature, high pressure, high dust and flame combustion environment condition inside the BF, in addition to the fluidization characteristics of the burden surface. With the fusion of high-temperature metallurgy, radar detection and image processing, a new BF surface deep-learning detection system based on energy weight was developed in this study to visualize the smelting status of a BF and digitize the information of the burden surface. First, the original burden surface echo spectrogram was captured using a frequency-modulated continuous wave radar with a high-temperature-resistant sensor. Second, the point cloud distribution map was constructed based on the principle of synthetic aperture radar (SAR) imaging. The coordinate transformation and matrix compensation were completed by the entropy weight method and Gamma correction to convert point cloud map to the burden surface grayscale image, constructing datasets for the network. Third, with a 3rd-order hourglass feature extraction network, a BF surface detection network based on the principle of YOLOv3 was designed and trained to predict the position of the burden surface in the grayscale image and track the changing trend of the burden line. The proposed method, which is tested on two steel plant datasets, achieved an average prediction precision of 99.74%. Finally, compared with the traditional burden line extraction algorithm, burden line oscillations and local outliers can be avoided by the proposed method. The continuous detection of the BF surface information was realized. [ABSTRACT FROM AUTHOR]

Existing Terahertz radar using CSAR mode has the problem of unsatisfactory imaging quality. The target and the noise are mixed in the full-aperture imaging result, which is difficult to use for automatic target recognition; and its sub-aperture-based imaging method not only does not completely solve this problem, but also brings about the problems of generating fake scattering points and the dependence on manual debugging. In view of the shortcomings of existing sub-aperture-based imaging methods, a Terahertz radar’s high-quality imaging method based on the sub-aperture is proposed by us. Among our research, 4 new methods, namely the sub-aperture division method which divides overlapping sub-apertures, the sub-aperture boundary point selection method, two new methods of selecting the sub-aperture boundary point, are used. The imaging method proposed by us further improves the signal-to-noise ratio of the target in the imaging result, and can be applied to targets with more complex shapes. Moreover, our imaging method solves the problems of generating fake scattering points and the dependence on manual debugging. After field test, our imaging method has better imaging quality than existing methods, and it is less dependent on manual debugging. [ABSTRACT FROM AUTHOR]

Image segmentation and classification of surfaces and obstacles in automotive radar imagery are the key technologies to provide valuable information for path planning in autonomous driving. As opposed to traditional radar processing, where clutter is considered as an unwanted return and should be effectively removed, autonomous driving requires full scene characterization. Hence, clutter carries necessary information for situational awareness of the autonomous platform and needs to be fully assessed to find the passable areas. In this paper, we proposed a method of automatic segmentation of automotive radar images based on two main steps: unsupervised image pre-segmentation using marker-based watershed transformation, followed by the supervised segmentation and classification of regions containing objects and surfaces based on the use of statistical distribution parameters. Several distributions were considered to characterize returns from specific region types of interest within the scene (denoted as classes) in calibrated radar imagery—the extracted distribution parameters were assessed for their ability to distinguish each class. These parameters were then used as features in a multivariate Gaussian distribution model classifier. Both the performances of the proposed supervised classification algorithm and the automatically segmented results were investigated using F1-score and Jaccard similarity coefficients, respectively. [ABSTRACT FROM AUTHOR]

This paper studies the methods of moving targets tracking based on a multi-beam tracking system in terahertz (THz) band, which is an initial attempt in this field. Taking the advantage of forming high resolution range profile of THz radar, a target geometric center tracking method is developed at first. However, the tracking performance is deteriorated by the severe angular glint and system disturbance. A further analysis on the experiment data finds a statistical correlation between the angular glint and the normalized amplitude variance, which is exploited to identify and exclude instable scatterers. A non-linear angular discrimination function is also established to deal with the anomalous measurement of the radar. Finally, an instable point exclusion method and a nonlinear angular discrimination method are proposed and combined to develop an improved tracking method, which can suppress angular glint and mitigate measuring perturbation, hence promoting the tracking performance. Proof-of-principle experiments are performed with a multi-beam tracking system working in 0.2 THz band. Tracking results of different targets demonstrate that the improved tracking method can effectively eliminate the tracking failure and significantly promote the tracking accuracy. [ABSTRACT FROM AUTHOR]

By exploiting the spatial-variant property of the inverse synthetic aperture radar (ISAR) imaging plane of a space target, interferometric ISAR (InISAR) can provide three-dimensional (3-D) images of space targets using fewer antennas than traditional InISAR imaging systems. This article analyzes InISAR imaging of space targets with monostatic radar. First, a more realistic ISAR imaging model for space targets is established, which adopts the rotation of the earth and can provide a mathematical apprehension of the movement of space targets in InISAR imaging. Next, a sequential phase unwrapping method for InISAR imaging of space targets with monostatic radar is proposed. Then, the performance indicator of this one-antenna InISAR system is provided with analysis of the impact of the influencing factors in InISAR imaging under different scenarios. Finally, numerical simulations are performed to validate the theoretical analysis and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Millimeter-wave (mmW) radars are being increasingly integrated into commercial vehicles to support new advanced driver-assistance systems (ADAS) by enabling robust and high-performance object detection, localization, as well as recognition - a key component of new environmental perception. In this paper, we propose a novel radar multiple-perspectives convolutional neural network (RAMP-CNN) that extracts the location and class of objects based on further processing of the range-velocity-angle (RVA) heatmap sequences. To bypass the complexity of 4D convolutional neural networks (NN), we propose to combine several lower-dimension NN models within our RAMP-CNN model that nonetheless approaches the performance upper-bound with lower complexity. The extensive experiments show that the proposed RAMP-CNN model achieves better average recall (AR) and average precision (AP) than prior works in all testing scenarios (see). Besides, the RAMP-CNN model is validated to work robustly under the nighttime, which enables low-cost radars as a potential substitute for pure optical sensing under severe conditions. [ABSTRACT FROM AUTHOR]

Frequency-diversity is a computational imaging technique that can offer all-electronic imaging systems by leveraging spatio-temporally incoherent radiation patterns as an enabling technology. This approach exhibits a significant contrast to conventional imaging modalities, such as synthetic aperture radars (SAR) and phased arrays in that the raster scanning requirement of a scene to be imaged (mechanical or electronic) can be broken and replaced by a quasi-random interrogation of the scene. This aspect of frequency-diverse computational imaging systems significantly simplifies the physical hardware requirements of conventional radars. Despite this advantage, the application of the frequency-diversity technique has been mostly limited to static imaging scenarios, where the position of the scene to be imaged remains fixed over the data acquisition cycle. This limitation hinders the frequency-diverse computational radars from being deployed for applications where the scene dynamics may vary over the data acquisition cycle, such as in automotive radars. In this paper, we demonstrate that by modifying the sensing matrix to account for the movement of the radar platform, frequency-diverse computational imaging radars can be successfully used in debris detection on roads. We show that operating within the frequency band of 77–81 GHz, the presented dynamic frequency-diverse radar technique can produce high fidelity point spread function (PSF) patterns eliminating the distortions caused by the motion of the radar. We also prove that the PSF patterns of the radar are in excellent agreement with theoretical diffraction limited resolution limits. [ABSTRACT FROM AUTHOR]

We propose an image reconstruction method to detect moving objects using multiple impulse radio ultra-wideband signals. In contrast with conventional methods, the proposed approach first reconstructs an image of changes of reflected ultra-wideband signals in the 2D domain, and then detects moving objects using the reconstructed 2D image. We believe that the proposed method is useful because not only it is based on effective 2D modeling of moving objects, but also it incorporates a priori information about the moving object images. We verified experimentally that the proposed method provided improved performance compared with the existing methods. [ABSTRACT FROM AUTHOR]

The accurate classification of activity patterns based on radar signatures is still an open problem and is a key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural network strategy with an autocorrelation pre-processing instead of the traditional micro-Doppler image pre-processing to classify activities or subjects accurately. The proposed strategy uses an iterative deep learning framework for the automatic definition and extraction of features. This is followed by a traditional supervised learning classifier to label different activities. Using three human subjects and their real motion captured data, 12 000 radar signatures were simulated by varying additive white Gaussian noise. In addition, 6720 experimental radar signatures were captured with a frequency-modulated continuous radar at 5.8 GHz with 400 MHz of instantaneous bandwidth from seven activities using one subject and 4800 signatures from five subjects while walking. The simulated and experimental data were both used to validate our proposed method, with signal–noise ratio varying from −20 to 20 dB and with 88.74% average accuracy at −10 dB and 100% peak accuracy at 15 dB. The proposed iterative convolutional neural networks followed with random forests not only outperform the feature-based methods using micro-Doppler images but also outperform the classification methods using other types of supervised classifiers after our proposed iterative convolutional neural network. [ABSTRACT FROM AUTHOR]

This paper discusses radar-based technologies that provide drivers with information about road curves under conditions in which optical sensors are unable to perform. The development of a task capable of estimating road curves has become a popular challenge since the commencement of the active development of advanced driver assistance systems and autonomous vehicles. Although the hardware implementation of a road curvature measurement system may have many variations, including cameras, we consider microwave sensors to be a reasonable alternative that offers many benefits. Road curvature measurement requires fast acquisition of the necessary data from a moving vehicle followed by efficient postprocessing of the data to identify a sufficient number of reliable featured points in the local environment. These points would enable a hypothesis about the dimensions and shape of the probable road geometry to be built. Different studies attempted to solve this problem using specialized equipment and custom-built algorithms. Our solution is to use a commercially available radar and some preprocessing and postprocessing algorithms for data conditioning and analysis to obtain reliable results in both day- and night-time environments and under various weather conditions in a relatively short time using a simplified approach based on circle-fitting algorithms. We confirmed the effectiveness of the proposed approach by conducting multiple road experiments with a commercially available microwave sensor. Considering that the road infrastructure is currently not optimized for road curvature measurements, the results we obtained with our proposed method (within 10%–17% of those on the actual map) are acceptable. [ABSTRACT FROM AUTHOR]