In modern war,radar countermeasure is becoming increasingly fierce,and the enemy jamming time and pattern are changing more randomly.It is challenging for the radar to efficiently identify jamming and obtain precise p...In modern war,radar countermeasure is becoming increasingly fierce,and the enemy jamming time and pattern are changing more randomly.It is challenging for the radar to efficiently identify jamming and obtain precise parameter information,particularly in low signal-to-noise ratio(SNR)situations.In this paper,an approach to intelligent recognition and complex jamming parameter estimate based on joint time-frequency distribution features is proposed to address this challenging issue.Firstly,a joint algorithm based on YOLOv5 convolutional neural networks(CNNs)is proposed,which is used to achieve the jamming signal classification and preliminary parameter estimation.Furthermore,an accurate jamming key parameters estimation algorithm is constructed by comprehensively utilizing chi-square statistical test,feature region search,position regression,spectrum interpolation,etc.,which realizes the accurate estimation of jamming carrier frequency,relative delay,Doppler frequency shift,and other parameters.Finally,the approach has improved performance for complex jamming recognition and parameter estimation under low SNR,and the recognition rate can reach 98%under−15 dB SNR,according to simulation and real data verification results.展开更多
The traversal search of multi-dimensional parameter during the process of hypersonic target echo signal coherent integration,leads to the problem of large amounts of calculation and poor real-time performance.In view ...The traversal search of multi-dimensional parameter during the process of hypersonic target echo signal coherent integration,leads to the problem of large amounts of calculation and poor real-time performance.In view of these problems,a modified polynomial Radon-polynomial Fourier transform(MPRPFT)hypersonic target coherent integration detection algorithm based on Doppler feedback is proposed in this paper.Firstly,the Doppler estimation value of the target is obtained by using the target point information obtained by subsequent non-coherent integration detection.Then,the feedback adjustment of the coherent integration process is performed by using the acquired target Doppler estimation value.Finally,the coherent integration is completed after adjusting the search interval of compensation.The simulation results show that the algorithm can effectively reduce the computational complexity and improve the real-time performance on the basis of the effective coherent integration of hypersonic target echo signals.展开更多
C&I(chopping and interleaving)干扰是一种针对线性调频(linear frequency modulation,LFM)雷达的典型干扰样式,干扰子信号调频斜率与雷达发射信号相同,利用信号处理工具分离真实回波与干扰信号难度较大。针对该问题,以LFM相参雷...C&I(chopping and interleaving)干扰是一种针对线性调频(linear frequency modulation,LFM)雷达的典型干扰样式,干扰子信号调频斜率与雷达发射信号相同,利用信号处理工具分离真实回波与干扰信号难度较大。针对该问题,以LFM相参雷达抗自卫式C&I干扰为背景,提出基于回波预处理和相参积累的干扰抑制算法。根据估计的回波时延,设置距离窗截取受干扰回波段,在此基础上,通过对回波预处理,改变不同重复周期内假目标的快时间位置分布,通过相参积累实现干扰抑制。仿真试验表明,所提算法能够有效抑制强干扰背景下的C&I干扰,干扰抑制后真实目标检测概率大幅提高,虚假目标数量明显减少。展开更多
目的伪装目标是目标检测领域一类重要研究对象,由于目标与背景融合度较高、视觉边缘性较差、特征信息不足,常规目标检测算法容易出现漏警、虚警,且检测精度不高。针对伪装目标检测的难点,基于YOLOv5(you only look once)算法提出了一种...目的伪装目标是目标检测领域一类重要研究对象,由于目标与背景融合度较高、视觉边缘性较差、特征信息不足,常规目标检测算法容易出现漏警、虚警,且检测精度不高。针对伪装目标检测的难点,基于YOLOv5(you only look once)算法提出了一种基于多检测层与自适应权重的伪装目标检测算法(algorithm for detecting camouflage targets based on multi-detection layers and adaptive weight,MAH-YOLOv5)。方法在网络预测头部中增加一个非显著目标检测层,提升网络对于像素占比极低、语义信息不足这类目标的感知能力;在特征提取骨干中融合注意力机制,调节卷积网络对特征信息不足目标的权重配比,使其更关注待检测的伪装目标;在网络训练过程中使用多尺度训练策略,进一步提升模型鲁棒性与泛化能力;定义了用于军事目标检测领域的漏警、虚警指标,并提出伪装目标综合检测指数。结果实验在课题组采集的伪装数据集上进行训练和验证。结果表明,本文方法在自制数据集上的平均精度均值(mean average precision,mAP)达到76.64%,较YOLOv5算法提升3.89%;漏检率8.53%、虚警率仅有0.14%,较YOLOv5算法分别降低2.75%、0.56%;伪装目标综合检测能力指数高达88.17%。与其他对比算法相比,本文方法的综合检测能力指数仅次于最先进的YOLOv8等算法。结论本文方法在识别精度、漏检率等指标上均有较大改善,具有最优的综合检测能力,可为战场伪装目标的快速高精度检测识别提供技术支撑和借鉴参考。展开更多
基金supported by Shandong Provincial Natural Science Foundation(ZR2020MF015)Aerospace Technology Group Stability Support Project(ZY0110020009).
文摘In modern war,radar countermeasure is becoming increasingly fierce,and the enemy jamming time and pattern are changing more randomly.It is challenging for the radar to efficiently identify jamming and obtain precise parameter information,particularly in low signal-to-noise ratio(SNR)situations.In this paper,an approach to intelligent recognition and complex jamming parameter estimate based on joint time-frequency distribution features is proposed to address this challenging issue.Firstly,a joint algorithm based on YOLOv5 convolutional neural networks(CNNs)is proposed,which is used to achieve the jamming signal classification and preliminary parameter estimation.Furthermore,an accurate jamming key parameters estimation algorithm is constructed by comprehensively utilizing chi-square statistical test,feature region search,position regression,spectrum interpolation,etc.,which realizes the accurate estimation of jamming carrier frequency,relative delay,Doppler frequency shift,and other parameters.Finally,the approach has improved performance for complex jamming recognition and parameter estimation under low SNR,and the recognition rate can reach 98%under−15 dB SNR,according to simulation and real data verification results.
基金supported by the National Natural Science Foundation of China(6173102361701519+1 种基金61671462)the Distinguished Taishan Scholars in Climbing Plan
文摘The traversal search of multi-dimensional parameter during the process of hypersonic target echo signal coherent integration,leads to the problem of large amounts of calculation and poor real-time performance.In view of these problems,a modified polynomial Radon-polynomial Fourier transform(MPRPFT)hypersonic target coherent integration detection algorithm based on Doppler feedback is proposed in this paper.Firstly,the Doppler estimation value of the target is obtained by using the target point information obtained by subsequent non-coherent integration detection.Then,the feedback adjustment of the coherent integration process is performed by using the acquired target Doppler estimation value.Finally,the coherent integration is completed after adjusting the search interval of compensation.The simulation results show that the algorithm can effectively reduce the computational complexity and improve the real-time performance on the basis of the effective coherent integration of hypersonic target echo signals.
文摘C&I(chopping and interleaving)干扰是一种针对线性调频(linear frequency modulation,LFM)雷达的典型干扰样式,干扰子信号调频斜率与雷达发射信号相同,利用信号处理工具分离真实回波与干扰信号难度较大。针对该问题,以LFM相参雷达抗自卫式C&I干扰为背景,提出基于回波预处理和相参积累的干扰抑制算法。根据估计的回波时延,设置距离窗截取受干扰回波段,在此基础上,通过对回波预处理,改变不同重复周期内假目标的快时间位置分布,通过相参积累实现干扰抑制。仿真试验表明,所提算法能够有效抑制强干扰背景下的C&I干扰,干扰抑制后真实目标检测概率大幅提高,虚假目标数量明显减少。
文摘目的伪装目标是目标检测领域一类重要研究对象,由于目标与背景融合度较高、视觉边缘性较差、特征信息不足,常规目标检测算法容易出现漏警、虚警,且检测精度不高。针对伪装目标检测的难点,基于YOLOv5(you only look once)算法提出了一种基于多检测层与自适应权重的伪装目标检测算法(algorithm for detecting camouflage targets based on multi-detection layers and adaptive weight,MAH-YOLOv5)。方法在网络预测头部中增加一个非显著目标检测层,提升网络对于像素占比极低、语义信息不足这类目标的感知能力;在特征提取骨干中融合注意力机制,调节卷积网络对特征信息不足目标的权重配比,使其更关注待检测的伪装目标;在网络训练过程中使用多尺度训练策略,进一步提升模型鲁棒性与泛化能力;定义了用于军事目标检测领域的漏警、虚警指标,并提出伪装目标综合检测指数。结果实验在课题组采集的伪装数据集上进行训练和验证。结果表明,本文方法在自制数据集上的平均精度均值(mean average precision,mAP)达到76.64%,较YOLOv5算法提升3.89%;漏检率8.53%、虚警率仅有0.14%,较YOLOv5算法分别降低2.75%、0.56%;伪装目标综合检测能力指数高达88.17%。与其他对比算法相比,本文方法的综合检测能力指数仅次于最先进的YOLOv8等算法。结论本文方法在识别精度、漏检率等指标上均有较大改善,具有最优的综合检测能力,可为战场伪装目标的快速高精度检测识别提供技术支撑和借鉴参考。
