RADAR TARGET RECOGNITION BASED ON NEURAL NETWORK

The problem of radar target recognition using range profiles is investigated in this paper, based on a Radial Basis Function Network(RBFN). A preprocessing method is proposed, which performs amplitude average of the range profiles to obtain more stable patterns. After pointing out the limitedness of traditional empirical formula, this paper also gives a method of estimating the shape parameter a of a Gaussian kernel function according-to spatial distribution of the training samples. It is shown that the method proposed in this paper offers promise for target recognition, from both the theoretical analysis and the experimental results of rotating platform imaging based on data acquired in a microwave anechoic chamber.

Deep convolutional neural network for meteorology target detection in airborne weather radar images

Considering the problem that the scattering echo images of airborne Doppler weather radar are often reduced by ground clutters,the accuracy and confidence of meteorology target detection are reduced.In this paper,a deep convolutional neural network(DCNN)is proposed for meteorology target detection and ground clutter suppression with a large collection of airborne weather radar images as network input.For each weather radar image,the corresponding digital elevation model(DEM)image is extracted on basis of the radar antenna scan-ning parameters and plane position,and is further fed to the net-work as a supplement for ground clutter suppression.The fea-tures of actual meteorology targets are learned in each bottle-neck module of the proposed network and convolved into deeper iterations in the forward propagation process.Then the network parameters are updated by the back propagation itera-tion of the training error.Experimental results on the real mea-sured images show that our proposed DCNN outperforms the counterparts in terms of six evaluation factors.Meanwhile,the network outputs are in good agreement with the expected mete-orology detection results(labels).It is demonstrated that the pro-posed network would have a promising meteorology observa-tion application with minimal effort on network variables or parameter changes.

ia-PNCC: Noise Processing Method for Underwater Target Recognition Convolutional Neural Network

Underwater target recognition is a key technology for underwater acoustic countermeasure.How to classify and recognize underwater targets according to the noise information of underwater targets has been a hot topic in the field of underwater acoustic signals.In this paper,the deep learning model is applied to underwater target recognition.Improved anti-noise Power-Normalized Cepstral Coefficients(ia-PNCC)is proposed,based on PNCC applied to underwater noises.Multitaper and normalized Gammatone filter banks are applied to improve the anti-noise capacity.The method is combined with a convolutional neural network in order to recognize the underwater target.Experiment results show that the acoustic feature presented by ia-PNCC has lower noise and are wellsuited to underwater target recognition using a convolutional neural network.Compared with the combination of convolutional neural network with single acoustic feature,such as MFCC(Mel-scale Frequency Cepstral Coefficients)or LPCC(Linear Prediction Cepstral Coefficients),the combination of the ia-PNCC with a convolutional neural network offers better accuracy for underwater target recognition.

High-accuracy target tracking for multistatic passive radar based on a deep feedforward neural network

In radar systems,target tracking errors are mainly from motion models and nonlinear measurements.When we evaluate a tracking algorithm,its tracking accuracy is the main criterion.To improve the tracking accuracy,in this paper we formulate the tracking problem into a regression model from measurements to target states.A tracking algorithm based on a modified deep feedforward neural network(MDFNN)is then proposed.In MDFNN,a filter layer is introduced to describe the temporal sequence relationship of the input measurement sequence,and the optimal measurement sequence size is analyzed.Simulations and field experimental data of the passive radar show that the accuracy of the proposed algorithm is better than those of extended Kalman filter(EKF),unscented Kalman filter(UKF),and recurrent neural network(RNN)based tracking methods under the considered scenarios.

Generalization Capabilities of Feedforward Neural Networks for Pattern Recognition

This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.

MOVING TARGETS PATTERN RECOGNITION BASED ON THE WAVELET NEURAL NETWORK

Based on pattern recognition theory and neural network technology, moving objects automatic detection and classification method integrating advanced wavelet analysis are discussed in detail. An algorithm of moving targets pattern recognition on the combination of inter-frame difference and wavelet neural network is presented. The experimental results indicate that the designed BP wavelet network using this algorithm can recognize and classify moving targets rapidly and effectively.

Research on Behaviour Recognition Method for Moving Target Based on Deep Convolutional Neural Network

Aiming at the problem that the average recognition degree of the moving target line is low with the traditional motion target behaviour recognition method, a motion recognition method based on deep convolutional neural network is proposed in this paper. A target model of deep convolutional neural network is constructed and the basic unit of the network is designed by using the model. By setting the unit, the returned unit is calculated into the standard density diagram, and the position of the moving target is determined by the local maximum method to realize the behavior identification of the moving target. The experimental results show that the multi-parameter SICNN256 model is slightly better than other model structures. The average recognition rate and recognition rate of the moving target behavior recognition method based on deep convolutional neural network are higher than those of the traditional method, which proves its effectiveness. Since the frequency of single target is higher than that of multiple recognition and there is no target similarity recognition, similar target error detection cannot be excluded.

Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images

As a classic deep learning target detection algorithm,Faster R-CNN(region convolutional neural network)has been widely used in high-resolution synthetic aperture radar(SAR)and inverse SAR(ISAR)image detection.However,for most common low-resolution radar plane position indicator(PPI)images,it is difficult to achieve good performance.In this paper,taking navigation radar PPI images as an example,a marine target detection method based on the Marine-Faster R-CNN algorithm is proposed in the case of complex background(e.g.,sea clutter)and target characteristics.The method performs feature extraction and target recognition on PPI images generated by radar echoes with the convolutional neural network(CNN).First,to improve the accuracy of detecting marine targets and reduce the false alarm rate,Faster R-CNN was optimized as the Marine-Faster R-CNN in five respects:new backbone network,anchor size,dense target detection,data sample balance,and scale normalization.Then,JRC(Japan Radio Co.,Ltd.)navigation radar was used to collect echo data under different conditions to build a marine target dataset.Finally,comparisons with the classic Faster R-CNN method and the constant false alarm rate(CFAR)algorithm proved that the proposed method is more accurate and robust,has stronger generalization ability,and can be applied to the detection of marine targets for navigation radar.Its performance was tested with datasets from different observation conditions(sea states,radar parameters,and different targets).

基于CNN-Swin Transformer Network的LPI雷达信号识别

针对在低信噪比(SNR)条件下,低截获概率雷达信号调制方式识别准确率低的问题,提出一种基于Transformer和卷积神经网络(CNN)的雷达信号识别方法。首先,引入Swin Transformer模型并在模型前端设计CNN特征提取层构建了CNN+Swin Transformer网络(CSTN),然后利用时频分析获取雷达信号的时频特征,对图像进行预处理后输入CSTN模型进行训练,由网络的底部到顶部不断提取图像更丰富的语义信息,最后通过Softmax分类器对六类不同调制方式信号进行分类识别。仿真实验表明:在SNR为-18 dB时,该方法对六类典型雷达信号的平均识别率达到了94.26%,证明了所提方法的可行性。

Arbitrary-oriented target detection in large scene sar images

Target detection in the field of synthetic aperture radar(SAR) has attracted considerable attention of researchers in national defense technology worldwide,owing to its unique advantages like high resolution and large scene image acquisition capabilities of SAR.However,due to strong speckle noise and low signal-to-noise ratio,it is difficult to extract representative features of target from SAR images,which greatly inhibits the effectiveness of traditional methods.In order to address the above problems,a framework called contextual rotation region-based convolutional neural network(RCNN) with multilayer fusion is proposed in this paper.Specifically,aimed to enable RCNN to perform target detection in large scene SAR images efficiently,maximum sliding strategy is applied to crop the large scene image into a series of sub-images before RCNN.Instead of using the highest-layer output for proposal generation and target detection,fusion feature maps with high resolution and rich semantic information are constructed by multilayer fusion strategy.Then,we put forwards rotation anchors to predict the minimum circumscribed rectangle of targets to reduce redundant detection region.Furthermore,shadow areas serve as contextual features to provide extraneous information for the detector identify and locate targets accurately.Experimental results on the simulated large scene SAR image dataset show that the proposed method achieves a satisfactory performance in large scene SAR target detection.

Human Activity Recognition Based on Frequency-Modulated Continuous Wave and DenseNet

With the development of wireless technology, Frequency-Modulated Continuous Wave (FMCW) radar has increased sensing capability and can be used to recognize human activity. These applications have gained wide-spread attention and become a hot research area. FMCW signals reflected by target activity can be collected, and human activity can be recognized based on the measurements. This paper focused on human activity recognition based on FMCW and DenseNet. We collected point clouds from FMCW and analyzed them to recognize human activity because different activities could lead to unique point cloud features. We built and trained the neural network to implement human activities using a FMCW signal. Firstly, this paper presented recent reviews about human activity recognition using wireless signals. Then, it introduced the basic concepts of FMCW radar and described the fundamental principles of the system using FMCW radar. We also provided the system framework, experiment scenario, and DenseNet neural network structure. Finally, we presented the experimental results and analyzed the accuracy of different neural network models. The system achieved recognition accuracy of 100 percent for five activities using the DenseNet. We concluded the paper by discussing the current issues and future research directions.

基于DenseNet和卷积注意力模块的高精度手势识别

非接触的手势识别是一种新型人机交互方式,在增强现实(AR)/虚拟现实(VR)、智能家居、智能医疗等方面有着广阔的应用前景,近年来成为一个研究热点。由于需要利用毫米波雷达进行更精确的微动手势识别,该文提出一种新型的基于MIMO毫米波雷达的微动手势识别方法。采用4片AWR1243雷达板级联而成的毫米波级联(MMWCAS)雷达采集手势回波,对手势回波进行时频分析,基于距离-多普勒(RD)图和3D点云检测出人手目标。通过数据预处理,提取手势目标的距离-时间谱图(RTM)、多普勒-时间谱图(DTM)、方位角-时间谱图(ATM)和俯仰角-时间谱图(ETM),更加全面地表征手势的运动特征,并形成混合特征谱图(FTM),对12种微动手势进行识别。设计了基于DenseNet和卷积注意力模块的手势识别网络,将混合特征谱图作为网络的输入,创新性地融合了卷积注意力模块(CBAM),实验表明,识别准确率达到99.03%,且该网络将注意力放在手势动作的前半段,实现了高精度的手势识别。

基于卷积神经网络的遥感图像目标识别仿真

在遥感图像中,目标往往位于复杂的地物背景中,包括不同类型的植被、土地覆盖、建筑物等。上述复杂的地物背景对目标识别造成了困难。为了精准识别遥感图像目标,提出一种卷积神经网络下遥感图像目标识别算法。将暗通道原理和双边滤波算法有效结合,对遥感图像展开增强处理。统计分析遥感图像目标尺度范围,通过训练和测试卷积神经网络,得到最佳目标感兴趣区域尺度。确定目标感兴趣区域最佳尺度后,构建基于卷积神经网络的遥感图像目标识别架构,完成遥感图像目标识别。通过实验分析证明,采用所提算法可以有效提升遥感图像增强效果,具有较好的遥感图像目标识别性能。

基于双流CNN-BiLSTM的毫米波雷达人体动作识别方法

目前基于雷达的人体动作识别方法,大多是先对人体动作的回波信号进行多维快速傅里叶变换(FFT)得到距离、多普勒和角度等信息,构造各种数据谱图后再输入到神经网络中进行分类识别,数据预处理过程较为复杂。提出了一种双流卷积神经网络(CNN)与双向长短时记忆网络(BiLSTM)串联的毫米波雷达人体动作识别方法。首先对原始的雷达回波信号复数采样数据(I/Q)进行帧差处理,以消除静态干扰,并将其转换为幅度/相位(A/P)的数据格式;然后将帧差后的I/Q和A/P数据分别输入单流的CNN-BiLSTM网络,提取人体动作的空间和时间特征,最后进行双流网络的融合以增强特征的交互性,提高识别准确率。实验结果表明,该方法数据预处理简单,并充分利用了动作数据的帧间相关性,模型收敛快,识别准确率可以达到99%,是一种快速有效的人体动作识别方法。

基于注意力机制的鸟类识别算法

针对现有细粒度鸟类目标识别算法准确率不高的问题,提出一种鸟类目标检测算法YOLOv5-Bird。首先,在YOLOv5主干网络中引入基于混合域的坐标注意力(CA)机制,增大有价值的通道权重,以区分目标特征和背景中的冗余特征;其次,在原始主干网络中采用双层路由注意力(BRA)模块替换原网络中的部分C3模块,过滤低相关度的键值对信息,获得高效的长距离依赖关系;最后,使用WIoU(Wise-Intersection over Union)损失函数,增强算法对目标的定位能力。实验结果表明,YOLOv5-Bird在自建数据集上取得了82.8%的精确率和77.0%的召回率,比YOLOv5算法分别提高4.3和7.6个百分点,也优于增加其他注意力机制的算法。验证了YOLOv5-Bird在鸟类目标检测场景中具有较好的性能。

人工智能时代的目标识别课程教学

目标识别的核心任务是判别图像的目标类型,通常采用机器学习算法完成,而鲁棒特征提取是其关键。传统人工提取的特征通常存在表达能力较弱的问题。深度学习理论的兴起为高精度目标识别提供了有效的解决途径,同时因其理论较为丰富,涉及面较广,给目标识别课程的讲授带来了新的挑战。通过设计具有专业特色的课程内容、构建知识链条、师生共建活跃课堂和全方位考核模式的探索等进行课程改革;在深度神经网络目标识别内容设计方面,侧重讲授关键概念、经典网络、研究进展及未来发展方向,为从事相关工作的教师和学生提供参考。

基于微多普勒角点特征与Non-Local机制的穿墙雷达人体步态异常终止行为辨识技术

穿墙雷达能够穿透建筑物墙体,实现室内人体目标探测。利用深度学习提取不同肢节点的微多普勒特征,可以有效辨识障碍物后的人体行为。但是,当生成训练、验证集与生成测试集的受试者不同时,基于深度学习的行为识别方法测试准确率相对验证准确率往往较低,泛化能力较差。因此,该文提出一种基于微多普勒角点特征与Non-Local机制的穿墙雷达人体步态异常终止行为辨识技术。该方法利用Harris与Moravec检测器提取雷达图像上的角点特征,建立角点特征数据集;利用多链路并行卷积和Non-Local机制构建全局上下文信息提取网络,学习图像像素的全局分布特征;将全局上下文信息提取网络重复堆叠4次得到角点语义特征图,经多层感知机输出行为预测概率。仿真和实测结果表明,所提方法可以有效识别室内人体步行过程中存在的坐卧、跌倒等突发步态异常终止行为,在提升识别准确率、鲁棒性的前提下,有效控制泛化精度误差不超过6.4%。

基于雅可比显著图的电磁信号快速对抗攻击方法

为了生成高质量的电磁信号对抗样本,提出了快速雅可比显著图攻击(FJSMA)方法。FJSMA通过计算攻击目标类别的雅可比矩阵,并根据该矩阵生成特征显著图,之后迭代选取显著性最强的特征点及其邻域内连续特征点添加扰动,同时引入单点扰动限制,最后生成对抗样本。实验结果表明,与雅可比显著图攻击方法相比,FJSMA在保持与之相同的高攻击成功率的同时,生成速度提升了约10倍,相似度提升了超过11%;与其他基于梯度的方法相比,攻击成功率提升了超过20%,相似度提升了20%~30%。

神经网络与水下目标识别研究型教学改革与创新实践

从舰船、潜艇、鱼雷、UUV、蛙人等水下目标识别在海洋国防战略中的重要性出发,以培养研究型、创新型、工程实践型人才为目标,以“为船为海为国防”的思想为引领,立足高校高水平研究生课程建设平台,改革神经网络与水下目标识别课程教学模式。将理论教学、科研研讨、工程实践相结合,开展神经网络与水下目标识别课程研究型教学改革与创新,培养专业知识基础扎实并具有科研素养的创新型人才。

基于改进的GoogleNet-ResNet算法的路基病害智能分类方法

针对路基病害分类算法存在的复杂病害辨识难度大、多视图雷达图像特征利用不充分等问题,提出一种基于改进的GoogleNet-ResNet算法的路基病害智能分类方法;首先,引入坐标注意力和改进的Inception模块对GoogleNet网络结构进行优化;然后,利用改进的GoogleNet学习c-scan数据特征剔除非目标病害,实现病害目标的粗分类;最后,将分类成病害的b-scan数据输入基于迁移学习的ResNet50,实现病害的细分类;实验表明,改进的GoogleNet进行病害粗分类的准确率可达到98.2%,检测速度可达90.9 fps;基于迁移学习的ResNet50进行病害细分类的准确率可达90.5%,检测速度可达52.6 fps;该算法的准确率比单独的改进的GoogleNet网络高10.1%,比单独的ResNet50网络高7.4%,有效地提高了道路路基病害的识别精度与效率。