Moving Target Detection Method Research Articles

Bionic ankle-assisted rehabilitation training system based on biomechanical evaluation

In modern society, people’s life rhythm is getting faster and faster. Ankle injury would significantly reduce the frequency of people’s activities, which has a great impact on people’s normal work and life. As a new medical method, the bionic ankle rehabilitation training system is used to assist rehabilitation doctors to help patients complete joint flexibility and recovery training. In the research method of ankle biomechanical characteristics, the detection of ankle joint patient’s motion is particularly important. The purpose of this paper is to study how to design a bionic ankle assisted rehabilitation training system based on image processing. Therefore, this paper proposes an image-based moving target detection method, which has the advantages of high reliability and simple operation, and can improve the recognition rate of the ankle joint movement. The experimental results of this paper showed that the system can realize the predetermined trajectory movement and run the system stably. In terms of patient following error, it was kept within 0.03cm. The following error of the ankle joint trajectory was up to 0.03cm and the lowest was 0.01cm, which was almost negligible. In terms of accuracy, the accuracy of the system was also very high, and it can respond and determine the patient’s actions quickly, thereby helping patients to better perform rehabilitation training.

Video SAR Moving Target Detection Method Based on Machine Vision

When detecting moving targets in video SAR, it is impossible to accurately obtain the moving targets in dynamic images. In order to solve the problems of low detection integrity and poor effectiveness, a video SAR moving target detection method based on machine vision is proposed. Firstly, the moving target pixel points are matched by the mixed Gaussian model to obtain the target area of the video SAR moving image; secondly, the HSV model and reflectivity algorithm are used to remove the shadows caused by the moving target; finally, the processed target area is input into the YOLO algorithm to complete the final video SAR moving target detection. Experimental results show that the proposed algorithm has high detection integrity, high detection rate, low false detection rate, and better detection effectiveness.

Multi-scale moving target detection with FDA-MIMO radar

The recently developed frequency diverse array (FDA) radar applies a small frequency increment across the array elements, which provides advantages in clutter suppression, jamming suppression, and target detection for existing radar systems. In this paper, the frequency increment is enlarged to guarantee that the transmit waveforms are orthogonal in frequency domain for multiple-input multiple-output (MIMO) radar. A multi-scale moving target detection method of FDA-MIMO radar is proposed. The FDA radar with a large frequency increment suffers from the deteriorated decorrelation of scatterers within the same range bin and causes the inner-bin range dependence (IRD) property in transmit spatial domain. By taking additional space–time snapshots in transmit domain as training samples, the space–time adaptive processing (STAP) is applied in joint receive and Doppler domain for clutter suppression, which alleviates the requirement of insufficient training samples in non-stationary clutter environment. In the sequel, a set of beamformers within the whole angular domain of interest is utilized for target detection, which achieves target detection under the condition of random target locations and sizes. Numerical simulation results are provided to verify the effectiveness of the proposed method.

Underwater weak moving target detection method based on wideband Multi-pulse coherent integration

When active sonar detects a weak moving target in a noisy background, coherent integration can be used to improve the signal-to-noise ratio of echo. The active sonar often transmits wideband signals and the target velocity ambiguity often occurs, in this case, the conventional coherent integration method makes the echo energy disperse and coherent integration gain decrease due to non-constant ambiguity factors in the bandwidth. To solve this problem, an underwater weak moving target detection method using multi-pulse coherent integration based on the wideband keystone transform is proposed. To compensate the non-constant ambiguity factors, a phase compensation function is constructed by replacing a single ambiguity factor with a set of ambiguity factors in the wideband keystone transform. After the proposed method, a well-focused image can be obtained in the delay-Doppler domain, and the coherent integration peak is detected to estimate delay and Doppler of the weak moving target. Simulations and lake test results verify the effectiveness of the proposed method, and show that the coherent integration gain with the proposed method is ca. 7–8 dB higher than that with the conventional method. The simulation results of integrating thirty pulses show that when the detection probability is greater than 0.7, the root-mean-square error of delay estimation of the proposed method is about 1/8 of that of the conventional method, and the root-mean-square error of Doppler estimation is about 1/3 of that of the conventional method, indicating that the proposed method has better parameter estimation accuracy.

Sports health information prediction system based on deep learning network

AbstractThis paper adopts the deep network model constructed the results of the training are used to explore the detection of sports, and to verify the deep learning network model from the perspective of reliability and feasibility. The experimental results in this paper show that the comprehensive performance evaluation index FM increased by 2.6%, Pr increased by 0.7%, and Re increased by 4.4%. Therefore, the deep residual network structure used in the DRNTL method proposed in this paper can effectively improve the generalization ability of the network. Through the learning of a large amount of labeled data, the model can be applied to the detection of other untrained complex scenes. The engineering of the moving target detection method is of great significance.

Static High Target-Induced False Alarm Suppression in Circular Synthetic Aperture Radar Moving Target Detection Based on Trajectory Features

The new mode of Circular Synthetic Aperture Radar (CSAR) has several advantages including multi-aspect and long-time observation, which can generate high-frame-rate image sequences to detect moving targets with a single-channel system. Nonetheless, due to CSAR being sensitive to 3D structures, static high targets are observed in scene display rotational motion within CSAR subaperture image sequences. Such motion can cause false alarms rising when utilizing image sequence-based moving target detection methods like logarithm background subtraction (LBS). To address this issue, this paper first thoroughly analyzes the moving target and static high target’s difference for the trajectory in an image sequence. Two new trajectory features of the rotation angle and moving distance are proposed to differentiate them. Based on the features, a new false alarm suppression method is proposed. The method first utilizes LBS to obtain coarse binary detection results comprising both moving and static high targets, then employs morphological filtering to eliminate noise. Next, DBSCAN and target tracking steps are employed to extract the trajectory features of the target and false alarm. Finally, false alarms are suppressed with trajectory-based feature discriminators to output detection results. The W-band CSAR open dataset is used to validate the proposed method’s effectiveness.

Range-Doppler Based Moving Target Image Trace Analysis Method in Circular SAR

The single channel Circular Synthetic Aperture Radar (CSAR) has the advantage of continuous surveillance of a fixed scene of interest, which can provide high frame rate image sequences to detect ground moving targets. Recent image-sequence-based CSAR moving target detection methods utilize the fact that the target signal moves fast in the image sequence. Knowledge of the target’s image trace(moving trace in the image sequence, which is equal to a target signature’s morphology in a full aperture CSAR image) can help design better detection methods. However, previous signature morphology studies are based on linear track geometry assumptions, which cannot handle CSAR’s nonlinear track. Hence, this paper proposes a new image trace method based on the range-Doppler principle. The proposed method can deduct the exact analytic function of an arbitrary moving target’s image trace in CSAR. The method assumes radar operates in side-looking mode and that the target moves on the ground plane. It combines the range-Doppler equations(i.e., iso-range and iso-Doppler relation) and Cartesian transformation between the ground and radar coordinate system to obtain the parametric functions of the image trace. Based on the method, three types of target motion (including linear and nonlinear motion) are analyzed. The proposed method is validated with both simulated and real data.

A Deep Learning-Based Moving Target Detection Method by Combining Spatiotemporal Information for ViSAR

A Deep Learning-Based Moving Target Detection Method by Combining Spatiotemporal Information for ViSAR

Radar Moving Target Detection Method Based on SET2 and AlexNet

Aiming at the nonstationary characteristics of echo signal for a high-speed maneuvering target, a signal feature extraction method is proposed by combining the time-frequency analysis and convolution neural network, and then the automatic detection of radar moving target in a noisy environment is realized. Firstly, the echo signal is modelled as a more accurate Gaussian modulation-linear frequency modulation (GM-LFM) signal and converted into the time-frequency image by a second-order synchroextracting transform (SET2). Then, ridge extraction is applied to extract the maximum energy ridge from the time-frequency distribution, and the data set is constructed by the maximum energy ridge. Finally, the data set is input into AlexNet for training, and the deep-level features of echo signal are extracted to realize the automatic moving targets detection. Simulation results show that SET2 and RE can effectively enhance the time-frequency characteristics of echo signal under the noisy environment, and the detection accuracy and noise robustness of the proposed method are better than that of SET1 and smooth pseudo-Wigner–Ville distribution (SPWVD).

Research on Motion Target Detection Method Based on Machine Learning

In the development of modern science and technology, due to the small size, low cost, practical operation is very flexible, so the UAV has been fully used in environmental monitoring, geological survey, military exploration, agricultural plant protection and other fields. Among them, as one of the basic contents of UAV aerial photography research, moving target detection directly affects the quality and efficiency of UAV work. On the basis of understanding the research status of moving target detection methods, I choose random forest and kernel correlation filtering algorithms for experimental analysis, focusing on the application value of the algorithm in moving target detection. Finally, the experimental results show that the proposed algorithm is effective.

Real-Time Non-Contact Millimeter Wave Radar-Based Vital Sign Detection

In this paper, the extraction of the life activity spectrum based on the millimeter (mm) wave radar is designed to realize the detection of target objects and the threshold trigger module. The maximum likelihood estimation method is selected to complete the design of the average early warning probability trigger function. The threshold trigger module is designed for the echo signal of static objects in the echo signal. It will interfere with the extraction of Doppler frequency shift results. The moving target detection method is selected, and the filter is designed. The static clutter interference is filtered without affecting the phase difference between the detection sequences, and the highlight target signal is improved. The frequency and displacement of thoracic movement are used as the detection data. Through the Fourier transform calculation of the sequence, the spectrum value is extracted within the estimated range of the heartbeat and respiration spectrum, and the heartbeat and respiration signals are picked up. The proposed design uses Modelsim and Quartus for CO-simulation to complete the simulation verification of the function, extract the number of logical units occupied by computing resources, and verify the algorithm with the vital signs experiment. The heartbeat and respiration were detected using the sports bracelet; the relative errors of heartbeat detection were 0–6.3%, the respiration detection was 0–9.5%, and the relative errors of heartbeat detection were overwhelmingly less than 5%.

A Ground Moving Target Detection Method for Seismic and Sound Sensor Based on Evolutionary Neural Networks

The accurate identification of moving target types in alert areas is a fundamental task for unattended ground sensors. Considering that the seismic and sound signals generated by ground moving targets in urban areas are easily affected by environmental noise and the power consumption of unattended ground sensors needs to be reduced to achieve low-power consumption, this paper proposes a ground moving target detection method based on evolutionary neural networks. The technique achieves the selection of feature extraction methods and the design of evolving neural network structures. The experimental results show that the improved model can achieve high recognition accuracy with a smaller feature vector and lower network complexity.

Moving target detection method based on CUR‐RPCA for missing array elements

Moving target detection performance is seriously affected by missing array elements for multichannel synthetic aperture radar (Multi-SAR) systems. Meanwhile, there is a contradiction between the accuracy of data recovery and the computational burden in traditional methods. To solve the problems, a moving target detection method based on CUR-RPCA for missing array elements is proposed in this paper. First, key nodes of the echo data are extracted and rearranged into a low-rank matrix. Then we uses the low-rank characteristic to complete key nodes of data. Subsequently, complete echo data is constructed by utilising recovered key nodes of data and CUR decomposition. Therefore using the ideas of CUR and RPCA, a novel optimization problem is constructed to achieve separation of moving targets and clutter while recovering data. In addition, only key nodes of the data is completed to achieve the performance of all data recovery, so that the disadvantage of low computational efficiency has been overcome for traditional matrix completion methods. Finally, the superior clutter suppression performance of the proposed method is verified by several numerical simulations and comparative studies.

Non-Line-of-Sight Moving Target Detection Method Based on Noise Suppression

At the present time, most of existing security systems only detect and track targets in line-of-sight (LOS). However, in practice, the locations of targets are often out of the line of sight. This article focuses on the non-line-of-sight (NLOS) moving target detection with low-power transmission signals by reflection. There are two key problems, the weak target echo signal and the multipath effect. In terms of the issues, this paper constructs the echo signal model of the NLOS target. On the basis of the echo model, the detection method of NLOS moving target based on millimeter-wave radar comes up, which is of great theoretical value and important practical significance for indoor security. This paper innovatively applies the polynomial fitting method to suppress static noise and range gating method to suppress noise from other range gates. Then, the location and velocity of the target are estimated by two-dimensional fast Fourier transform (FFT) and the multiple signal classification (MUSIC) method. Furthermore, in order to verify the accuracy of the NLOS target echo signal model proposed in this paper, we respectively simulated two important parts of the signal in the model, the target echo signal and the direct backscattered signal of the intermediate interface, both of which are multipath signals. We counted the echo path length distribution in these two parts, and applied the NLOS target detection method to process them respectively. In addition, we also simulated the NLOS target echo signal and obtained actual data in the actual scene, and processed both the simulated data and the actual data. Comparing the results of target detection with and without denoising methods, the effectiveness of the two denoising methods proposed in this paper is verified.

A Novel Detection Scheme in Image Domain for Multichannel Circular SAR Ground-Moving-Target Indication.

Circular synthetic aperture radar (CSAR), which can observe the region of interest for a long time and from multiple angles, offers the opportunity for moving-target detection (MTD). However, traditional MTD methods cannot effectively solve the problem of high probability of false alarm (PFA) caused by strong clutter. To mitigate this, a novel, three-step scheme combining clutter background extraction, multichannel clutter suppression, and the degree of linear consistency of radial velocity interferometric phase (DLRVP) test is proposed. In the first step, the spatial similarity of the scatterers and the correlation between sub-aperture images are fused to extract the strong clutter mask prior to clutter suppression. In the second step, using the data remaining after elimination of the background clutter in Step 1, an amplitude-based detector with higher processing gain is utilized to detect potential moving targets. In the third step, a novel test model based on DLRVP is proposed to further reduce the PFA caused by isolated strong scatterers. After the above processing, almost all false alarms are excluded. Measured data verified that the PFA of the proposed method is only 20% that of the comparison method, with improved detection of slow and weakly moving targets and with better robustness.

Octave convolution-based vehicle detection using frame-difference as network input

Vehicle detection in video frames has been treated the same way detecting vehicle for an isolated image. However, the models designed for the isolated image are blind to fast-moving vehicles and cannot localize the moving targets partially occluded in the scene. In this case, we figure out a way to combine the classic moving target detection method with the neural network method. In this work, first, we propose to add three-differential-frames into the neural network of Yolov3 as the second input which contains the motion information on the front and back frames to detect vehicles partially occluded; second, we reform the network by using Octave Convolution to reduce memory and computational cost while boosting accuracy. We experimentally show that by using the aforementioned methods together, compared with using original YOLOv3 on UA-DETRAC data set, AP is increased by 2.31%, recall is increased by 4.01%, and precision is increased by 3.10%. We demonstrate that the proposed method is indeed effective.

Researching a Moving Target Detection Method Based on Magnetic Flux Induction Technology

The ocean is a very important arena in modern warfare where all marine powers deploy their military forces. Due to the complex environment of the ocean, underwater equipment has become a very threatening means of surprise attack in modern warfare. Therefore, the timely and effective detection of underwater moving targets is the key to obtaining warfare advantages and has important strategic significance for national security. In this paper, magnetic flux induction technology was studied with regard to the difficulty of detecting underwater concealed moving targets. Firstly, the characteristics of a magnetic target were analyzed and an equivalent magnetic dipole model was established. Secondly, the structure of the rectangular induction coil was designed according to the model, and the relationship between the target’s magnetism and the detection signal was deduced. The variation curves of the magnetic flux and the electromotive force induced in the coil were calculated by using the numerical simulation method, and the effects of the different motion parameters of the magnetic dipole and the size parameters of the coil on the induced electromotive force were analyzed. Finally, combined with the wavelet threshold filter, a series of field tests were carried out using ships of different materials in shallow water in order to verify the moving target detection method based on magnetic flux induction technology. The results showed that this method has an obvious response to moving targets and can effectively capture target signals, which verifies the feasibility of the magnetic flux induction detection technology.

Accurate detection method of moving target based on sequential SAR images with multiple azimuth squint angles

In this paper, a novel moving target detection method for sequential Synthetic Aperture Radar (SAR) images with different azimuth-squint angles is proposed. In sequential SAR images, due to the movement of the target, the imaging position of moving targets among different frames differs. The method proposed in this paper uses this kind of motion characteristics to achieve the detection of moving targets in multi-frame SAR images. This algorithm can be divided into two parts: block-level detection and pixel-level detection. Block-level detection is achieved by stacked denoising autoencoders to extract the high-dimensional features of the moving target. Pixel-level detection consists of Local Binary Similarity Patterns (LBSP) coding as well as grayscale background subtraction. Pixel-level detection only needs to consider the pixels of foreground image pieces which contain moving targets. This method can not only increase the detection speed, but also suppress the false alarm problem caused by clutter. Experiments are carried out for verifying the validation of the method and the comparison are made between the proposed method and the traditional Constant False Alarm Rate (CFAR) algorithm.

Phase-Based GLRT Detection of Moving Targets with Pixel Tracking in Low-Resolution SAR Image Sequences

Spaceborne synthetic aperture radar (SAR) can provide ground area monitoring with large coverage. However, achieving a wide observation scope comes at the cost of resolution reduction owing to the trade-off between these parameters in conventional SAR. In low-resolution imaging, the moving target appears unresolved, weakly scattered, and slow moving in the image sequence, which can be generated by the subaperture technique. This article proposes a novel moving target detection method. First, interferometric phase statistics are combined with the generalized likelihood ratio test detector. A pixel tracking strategy is further exploited to determine whether a motion signal is present. These methods rely on the approximation of both clutter and noise statistics using Gaussian distributions in a low-resolution scenario. In addition, the motion signals are imaged with a subpixel offset. The proposed method is primarily validated using four real image sequences from TerraSAR-X data, which represent two types of homogeneous areas. The results reveal that moving targets can be detected in nearby areas using this strategy. The method is compared with the stack averaged coherence change detection and particle-filter-based tracking strategies.

Moving Target Shadow Analysis and Detection for ViSAR Imagery

The video synthetic aperture radar (ViSAR) is a new application in radar techniques. ViSAR provides high- or moderate-resolution SAR images with a faster frame rate, which permits the detection of the dynamic changes in the interested area. A moving target with moderate velocity can be detected by shadow detection in ViSAR. This paper analyses the frame rate and the shadow feature, discusses the velocity limitation of ViSAR moving target shadow detection and quantitatively gives the expression of velocity limitation. Furthermore, a fast factorized back projection (FFBP) based SAR video formation method and a shadow-based ground moving target detection method are proposed to generate SAR videos and detect the moving target shadow. The experimental results with simulated data prove the validity and feasibility of the proposed quantitative analysis and the proposed methods.