Fractal-based weak target detection within sea clutter

The target on the sea surface is complex and difficult to detect due to the interference of backscattered returns from the sea surface illuminated by the radar pulse. Detrended fluctuation analysis （DFA） has been used successfully to extract the time-domain Hurst exponent of sea-clutter series. Since the frequency of the sea clutter mainly concentrates around Doppler center so that we consider to extract frequency-do- main fractal characterization and then detect a weak target within sea clutter by using the difference of frequency-domain fractal characterization. The generalized detrended fluctuation analysis （GDFA） is more flexible than traditional DFA owing to its smoothing action for the clutters. In this paper, we apply the GDFA to evaluate the generalized Hurst exponent of sea-clutter series in the frequency domain. The difference of generalized Hurst exponents between different sea-clutter range bins would be used to determine whether the target exists. Moreover, some simulations with the real IPIX radar data have also been demonstrated in order to suooort this conclusion.

M-FCN based sea-surface weak target detection

This paper focuses on the sea-surface weak target detection based on memory-fully convolutional network(M-FCN)in strong sea clutter.Firstly,the constant false alarm rate(CFAR)detection method utilizes a low threshold with high probability of false alarm to detect sea-surface weak targets after non-coherent integration.Reducing the detection threshold can generate a large number of false alarms while increasing the detection rate,and how to suppress a large number of false alarms is the key to improve the performance of weak target detection.Then,the detection result of the low threshold is operated to construct the target matrix suitable for the size of fully convolutional networks and the convolution operator form.Finally,the M-FCN architecture is designed to learn the different accumulation characteristics of the target and the sea clutter between different frames.For improving the detection performance,the historical multi-frame information is memorized by the network,and the end-to-end structure is established to detect sea-surface weak target automatically.Experimental results on measured data demonstrate that the M-FCN method outperforms the traditional track before detection(TBD)method and reduces false alarm tracks by 35.1%,which greatly improves the track quality.

Detection of weak target for MIMO radar based on Hough transform

An effective method of multiple input multiple output （MIMO） radar weak target detection is proposed based on the Hough transform. The detection time duration is divided into multiple coherent processing intervals （CPIs）. Within each CPI, conventional methods such as fast Fourier transform （FFT） is exploit to coherent inte- grating in same range cell. Furthermore, noncoherent integration through several range cells can be implemented by Hough transform among all CPIs. Thus, higher integration gain can be obtained. Simulation results are also given to demonstrate that the detection performance of weak moving target can be dramatically improved.

Multiframe track-before-detect method based on velocity filtering in mixed coordinates

In this paper,a velocity filtering based track-before-detect algorithm in mixed coordinates is presented to address the problem of integration loss caused by inaccurate motion model in polar coordinate sensors.Since the motion of a con-stant velocity(CV)target is better modeled in Cartesian coordi-nates,the search of measurements for integration in polar sensor coordinates is carried out according to the CV model in Cartesian coordinates instead of an approximate model in polar sensor coordinates.The position of each cell is converted into Cartesian coordinates and predicted according to an assumed velocity.Then,the predicted Cartesian position is converted back to polar sensor coordinates for multiframe accumulation.The use of the correct model improves integration effectiveness and consequently improves algorithm performance.To handle the weak target with unknown velocity,a velocity filter bank in mixed coordinates is presented.The influence of velocity mis-match on the performance of filter bank is analyzed,and an effi-cient strategy for filter bank design is proposed.Numerical re-sults are presented to demonstrate the effectiveness of the pro-posed algorithm.

基于全卷积网络的复杂背景红外弱小目标检测研究

针对复杂背景红外弱小目标检测过程中存在的检测误差率高,检测时间过长等问题,提出基于全卷积网络的复杂背景红外弱小目标检测方法。分析复杂背景红外弱小目标检测的研究进展,找出不同方法的缺陷,采集红外图像,提取目标检测特征,并采用全卷积网络设计弱小目标检测的分类器,实现复杂背景红外弱小目标检测。实验结果表明,该方法的复杂背景红外弱小目标检测精度超过97%,具有较高的实际应用价值。

基于模糊神经网络的舰船雷达图像弱小目标检测

舰船雷达图像信息的维度较高,导致弱小目标的关键特征难以被精准提取,降低了弱小目标检测的可靠性,因此提出一种基于模糊神经网络的舰船雷达图像弱小目标检测方法。该方法对舰船雷达图像进行背景校正,利用图像灰度值加性模型从图像中提取弱小目标。最后将提取的弱小目标输入到模糊神经网络中,输出的结果即为舰船雷达图像弱小目标检测结果。通过实验证明,在不同高斯噪声环境中,该方法能够准确地检测出雷达图像中的弱小目标,并具有较快的检测速度。

A real-time detection and positioning method for small and weak targets using a 1D morphology-based approach in 2D images

A small and weak target detection method is proposed in this work that outperforms all other methods in terms of real-time capability.It is the first time that two-dimensional(2D)images are processed using only one-dimensional1D structuring elements in a morphology-based approach,enabling the real-time hardware implementation of the whole image processing method.A parallel image readout and processing structure is introduced to achieve an ultra-low latency time on the order of nanoseconds,and a hyper-frame resolution in the time domain can be achieved by combining the row-by-row structure and the electrical rolling shutter technique.Experimental results suggest that the expected target can be successfully detected under various interferences with an accuracy of 0.1 pixels(1σ)under the worst sky night test condition and that a centroiding precision of better than 0.03 pixels(1σ)can be reached for static tests.The real-time detection method with high robustness and accuracy is attractive for application to all types of real-time small target detection systems,such as medical imaging,infrared surveillance,and target measurement and tracking,where an ultra-high processing speed is required.

紧凑型地波雷达目标检测跟踪一体化实验平台

紧凑型地波雷达检测目标时回波信噪比低。应用传统的先检测后跟踪方法进行目标探测时,弱目标回波容易淹没在杂波和噪声中,出现弱目标漏检和虚假点迹误检,导致跟踪时易发生航迹断裂、误跟踪等现象,影响目标跟踪的连续性。为提升紧凑型地波雷达对海上运动目标的长时跟踪能力,建立检测器与跟踪器之间的信息动态交互机制,提出一种紧凑型地波雷达目标检测跟踪一体化方法。实验结果表明,与先检测后跟踪方法相比,所提方法跟踪得到的平均航迹时长增加了17.52 min。结合工程应用需求,在Matlab R2018b环境下开发了紧凑型地波雷达目标检测跟踪一体化实验平台,为紧凑型地波雷达海上目标探测实验测试提供了平台支撑。

Multiframe weak target track-before-detect based on pseudo-spectrum in mixed coordinates

Traditional multiframe Track-Before-Detect(TBD)may incur adverse integration loss resulting from model mismatch in sensor coordinates.Its suboptimal integration strategy may cause target envelope degradation.To address these issues,a pseudo-spectrum-based multiframe TBD in mixed coordinates is proposed firstly.The data search for energy integration is conducted based on an accurate model in the x-y plane while target energy is integrated based on pseudo-spectrum in sensor coordinates.The algorithm performance is improved since the model mismatch is eliminated,and the pseudo-spectrum based integration facilitates well maintained target envelope.The detailed multiframe integration procedure and theoretical target integrated envelope are derived.Secondly,to cope with the unknown target velocity,a velocity filter bank based on pseudo-spectrum in mixed coordinates is proposed.The effect of velocity mismatch on algorithm performance is analyzed and an efficient method for filter bank design is presented.Thirdly,a parameter estimation method using characteristics of integrated envelope is presented for improved target polar position and Cartesian velocity estimation.Finally,numerical results are provided to demonstrate the effectiveness of the proposed method.

复杂水文微弱多目标激光探测仿真与实验

为了探究在近岸复杂水体中激光探测对微弱目标的探测能力,研究水质、目标特征、目标距离对水下激光探测的影响具有重要理论和应用价值。论文建立了水下微弱目标激光探测模型,采用蒙特卡洛仿真验证了不同浊度微弱多目标激光探测性能,模拟了不同距离下微弱目标的激光后向散射回波信号,对多个不同反射系数的目标后向散射回波特性进行了分析。同时设计并研制了灵巧便携式水下微弱目标激光探测系统,进行了实验室及外场湖泊环境下的多目标探测、测距测试验证。在浊度为12.87 NTU的近岸湖泊水域,该系统可在10 m范围内对3~4个直径为80~400μm的不同低反射系数的混合小目标进行有效探测,平均测量误差为±0.11 m,与理论仿真结果一致。本文研究结果可为蓝绿激光水下多微弱目标探测链路计算、系统设计及参数优化提供参考,可以支撑近海浑浊水体下水下障碍物激光探测工程实践。

一种基于组合子阵协方差矩阵的阵列扩展方法

针对阵列在低信噪比条件下信号检测概率低且方位估计性能下降的问题,提出一种基于组合子阵协方差矩阵的线列阵扩展方法。该方法将阵列划分为奇偶子阵,根据子阵的互协方差与自协方差矩阵构建扩展接收数据,对扩展接收数据进行组合作为最终的阵列接收数据进行处理,由此在突破阵列物理孔径的基础上避免仅使用奇偶阵元互协方差重构接收数据时产生的栅瓣问题。仿真结果表明:新方法可以降低波束输出的旁瓣,具有较好的弱目标检测能力和方位分辨力;相比于基于奇偶阵元互协方差的阵列扩展方法,新方法可有效提升方位估计精度,且不存在栅瓣问题。

用于水下声呐目标检测的弱特征共焦通道调控方法

声呐图像视觉检测是复杂水域资源勘探和水下异物目标探测领域的重要技术之一。针对声呐图像中小目标存在的特征微弱和背景信息干扰问题,本文提出弱特征共焦通道调控水下声呐目标检测算法。为了提高模型对弱小目标的信息捕获和表征能力,设计弱小目标特征激活策略,并引入先验框尺度校准机制匹配底层语义特征检测分支,以提高小目标检测精度。应用全局信息聚合模块深入挖掘弱小目标的全局特征,避免冗余信息覆盖小目标微弱关键特征。为解决传统空间金字塔池化易忽视通道信息的问题,提出共焦通道调控池化模块,保留有效通道域小目标信息并克服复杂背景信息干扰。实验结果表明,本文所提模型在水下声呐数据集的9类弱小目标识别的平均检测精度达83.3%,相较基准提高了5.5%,其中铁桶、人体模型和立方体检测精度得到显著提高,分别提高24%、8.6%和7.3%,有效改善水下复杂环境中弱小目标漏检和误检问题。

基于YOLOv5水下目标检测算法研究与改进

在水下目标生物的检测过程中,由于水下环境恶劣,水中光线衰弱,以及大多水下生物以小目标的形态出现等问题,使得目前的水下目标检测带来了精度损失问题,为解决相应问题,给出了一种基于YOLOv5s改进的YOLOv5s-water算法来解决。首先通过STR(Swin-Transformer)旋转窗口来对YOLOv5s的主干层(Backbone)部分进行更改,提高模型的泛化能力,进而解决水下环境恶劣以及检测目标形态变化带来的问题。使用FReLU激活函数与CBAM注意力神经机制结合成的FCM注意力机制,将其嵌入到YOLOv5s的骨干网(Neck)部分,以用来突出目标特征并抑制次要信息,从而提高算法精度,加强小目标的特征提取。小目标检测方面,在YOLOv5结构上增加小目标检测头,以提高感受野,进而提高小目标的检测精度。仿真和实验结果表明:所提方法相较于YOLOv5s检测准确率P上升1.47%,精确度mAP@0.5上升2.76%,小目标检测效果明显,证明了方法的有效性。

一种基于ResNet的雷达弱小目标检测方法

为了解决恒虚警率(Constant False Alarm Rate,CFAR)检测算法对雷达弱小目标检测困难的问题,研究了基于卷积神经网络(Convolutional Neural Network,CNN)的目标检测方法。充分利用神经网络在特征提取上的优良性能,提出了一种基于残差网络(Residual Network,ResNet)块的雷达弱小目标检测方法。突破了传统方法仅利用幅度信息进行目标检测的框架,充分挖掘雷达回波数据中目标的相位特征作为神经网络目标分类检测的依据。经实验验证,所提出的方法在目标回波信噪比仅有-7 dB情况下,仍可实现50%以上的发现概率,并且随着信噪比的降低,所提方法的优异性越发明显。

Iterative Algorithm of Steered Minimum Variance and Its Application in Weak Targets Detection

The steered covariance matrix(STCM) and its inverse matrix should be calculated in each beam for steered minimum variance(STMV) . The inverse matrix needs complex computation and restricts its application in engineering. Combining the integration character of one-phase regressive filter with the iterative formula of inverse matrix,an STMV iterative algorithm is proposed. The computational cost of the iterative algorithm is reduced approximately to be 2/M times of the original one when there are M sensors,and is more advantaged for the realization of the algorithm in real time. Simulation results show that the STMV iterative algorithm can preserve the characters of STMV on high azimuth resolution and weak target detection while the computational cost reduced sharply. The analysis on sea trial data proves that the proposed algorithm can estimate each target's azimuth even when the source powers differ in large scales or their bearings are very approximate.

基于随机共振的水下目标微弱回波信号增强检测

针对低信噪比下主动声呐探测水下目标的微弱回波信号检测难题,本文提出了一种基于随机共振的微弱回波信号增强检测方法。该方法通过建立频移变尺度随机共振系统,与输入高频微弱回波信号、随机噪声相匹配,实现微弱回波信号的共振增强;进而利用乘积谱与谱峭度构建目标回波亮点增强检测指标,有效提升微弱回波亮点的能量集中程度,抑制杂波及虚假成分干扰。仿真结果表明:在低信噪比下,随机共振系统输出信噪比增益可达5 dB以上,微弱目标回波亮点检测结果更加直观便捷,杂波干扰得到大幅抑制。海试数据处理结果进一步验证了所提方法的有效性和可靠性。

微弱目标检测研究综述

微弱目标检测是安全检测中的一项基础性技术,在海面监测、空中微弱目标检测、网络威胁发现等应用场景具有重要实用价值。由于大尺度场景下存在信噪比低、背景变化大等问题,导致微弱目标检测易出现虚警、漏检等问题,微弱目标检测一直是目标检测领域的研究难点和热点。根据检测图像使用的方法不同,微弱目标检测方法分为单帧型和多帧型两大类,单帧型方法的检测速度快,但在复杂场景下表现不佳,而多帧型方法提高了准确性但需要更多资源。未来,在深度学习和人工智能技术的推动下,微弱目标检测不仅将聚焦于提高检测的准确性和效率,还将探索更加复杂的应用场景,如在动态和多变环境中的实时检测,具有广阔的应用前景。

强噪声中检测微弱目标信号特征的量子信号处理算法

随着噪声功率的增强,微弱目标信号的特征受噪声污染变得模糊且难以区分,导致微弱信号检测算法失效,提出一种可以保护目标信号特征的量子信号处理方法——局域半经典信号分析算法。详细介绍了算法实现量子化的原理和在量子域中保护目标信号特征的性质;给出算法步骤以及重要参数的计算方式;将所提算法与奇异值分解、小波阈值降噪算法结合进行了仿真分析和实验验证。结果表明,所提算法保护目标信号特征的能力可以帮助降噪算法检测极低信噪比的微弱信号,与其他方法结合可极大改善信噪比,准确提取信噪比为-30 dB的微弱目标信号,算法性能优越。

基于Prewitt算子和Radon变换的雷达高速微弱目标检测

正交频分复用(OFDM)调制雷达中跨距离单元走动问题降低了高速微弱目标检测性能,为此,提出一种基于Prewitt算子和Radon变换的OFDM雷达高速微弱目标检测算法。首先分析了多脉冲积累出现的跨距离单元走动以及Radon变换受噪声干扰问题,然后采用Prewitt算子卷积运算抑制噪声并保留回波能量,采用Radon变换沿距离单元走动斜线进行能量积累。理论分析和仿真结果表明,该算法具有比Hough变换和动目标检测(MTD)更优的低信噪比背景下的高速微弱目标检测性能,并能有效实现多目标检测。

一种时域降维多帧处理的Radon域弱目标检测

对于低分辨率的警戒雷达,在强杂波背景下检测低空慢速小目标("低、慢、小")是一个具有挑战性的难题.该文提出一种基于时域降维多帧数据联合处理的Radon域"低、慢、小"目标检测新方法.该方法首先通过单帧数据的自适应杂波抑制和多帧数据的有序统计恒虚警滤波器处理,抑制掉部分强杂波;然后,对经过两级杂波抑制后的时间距离域数据进行时间维的降维和平滑;最后,对时间距离像进行Radon变换,将时间距离域的目标检测问题转化为Radon参数空间的特征提取问题,通过设置两级门限提取出微弱目标.由于时域降维处理在Radon域增大了目标相对于杂波的角度偏移量,因此,该方法不仅可检测到低速目标,还能估计出目标速度.实测数据处理结果验证了该方法的有效性.