含旋转部件的动态目标ISAR成像及微多普勒特征提取

含旋转部件的动态目标ISAR成像中,受旋转部件微多普勒调制影响,导致目标成像质量下降,给目标识别带来巨大困难.抑制或消除旋转部件回波是处理带有旋转部件目标ISAR成像的重要内容.现有的算法在处理旋转部件时采用了单个旋转点的假设,虽然取得了较好的效果,但是对实测数据分离效果不明显.为此,本文基于含旋转部件目标主体和旋转部...     

含旋转部件目标双基地ISAR微动特征提取及成像研究

由于空间的高度复杂性,双基地雷达系统中目标微动产生的微多普勒信息与单基地体制雷达有较大区别。该文以含旋转结构部件目标为例,推导了双基地ISAR系统中目标微动产生的微多普勒效应,并详细分析了其在距离-慢时间2维谱图域内的表现形式及特点。针对双基地雷达收、发分置的特殊空间结构的影响,修正了基于扩展Hough变换的目标微动信息谱图域提取方法,并通过仿真验证了修正方法在双基体制ISAR成像系统中的有效性。     

基于自适应chirplet变换的ISAR瞬时成像的快速算法

在逆合成孔径雷达(ISAR)瞬时成像中,针对自适应chirplet分解方法运算量大,对信号的逼近精度有限等问题,提出了一种瞬时成像快速算法。该方法在参数粗搜索的基础上,将多维参数搜索过程转化为超越方程的求解问题。与传统方法比较,该方法不仅运算速度快,计算量小,而且参数估计精度高。仿真和真实雷达数据用此方法均能成出质量较好的ISAR图像。因而此快速算法是一种有效的ISAR瞬时成像的快速算法。     

基于复数局部均值分解的含旋转部件目标微多普勒分离技术

针对逆合成孔径雷达成像中某些含旋转部件的雷达目标,其回波由于受到旋转部件微多普勒的影响,从而导致目标主体成像质量下降的问题,该文研究了基于复数局部均值分解的微多普勒分离方法。该文通过分析目标主体和旋转部件回波分量的多普勒差异,并利用复数局部均值分解方法精确分离信号中内含的振荡模式,自适应地从高频至低频将复杂非平稳信号分解成若干个平稳的单分量信号,从而实现微多普勒信号分离。通过将微多普勒信号和目标主体回波进行分离,可以提高目标主体的成像质量,并能更好地获得旋转部件的微动参数特征。仿真和实测数据的结果证明了该方法的有效性。     

具有旋转部件雷达目标ISAR成像新方法

分析了具有旋转部件的运动目标回波信号的特点,提出了以单频信号和正弦调频信号为原子的双信号集匹配分解法。利用该算法,可以从含有单频分量和正弦调频分量的信号中检测出单频分量和正弦调频分量及其参数。将其应用于具有旋转部件目标的ISAR成像和微多普勒特征提取中,可以分离目标主体的回波分量和旋转部件回波分量,从而获得聚焦清晰的目标主体像并提取旋转部件特征。最后,仿真结果验证了该算法的有效性。     

雷达目标的散射中心建模研究

雷达目标总散射场可近似为若干散射中心贡献的叠加,而每一个散射中心都对应着特定的电磁散射机理,这些特定散射机理的散射场可表示成输入为雷达参数（频率、极化、视向角）和目标参数（几何、材料）的参数化模型.散射中心参数化模型在雷达回波实时模拟、半实物仿真、雷达目标识别等领域得到了广泛的关注.文中总结了雷达散射中心模型的发展历程,包括散射中心数学模型和散射中心参数提取方法,以及散射中心建模的难点问题和未来的研究方向.期望该文可为从事该方面研究的科研人员提供一些参考.     

雷达目标二维结构成像方法研究

该文首先研究了雷达目标二维电磁散射的频域散射模型;而后提出了用参数估计方法实现目标ISAR成像的思想,并研究了MP2D参数估计方法;最后用仿真数据和波音727客机真实目标实测数据对该方法进行了实验验证。实验结果表明,该方法能准确估计目标的二维散射中心,且对噪声有较强的抑制能力。     

基于ISAL的含旋转部件目标成像及微动特征提取

逆合成孔径激光雷达能实现对目标的高分辨2维成像,但如果目标中包含旋转部件,旋转部件回波带来的微多普勒效应会对目标的成像造成干扰。该文提出一种含旋转部件目标微多普勒特征提取及成像方法,首先利用匹配参考信号的方法对回波信号进行一定程度的非线性补偿,然后通过二值数学形态学方法提取频率-慢时间谱图中微多普勒特征曲线的信息,并利用微多普勒特征曲线的周期性进行曲线分离,实现对目标旋转部件微动参数的快速提取。在此基础上,对主体回波信号和旋转部件回波信号进行分离,完成对目标主体的2维成像。仿真实验验证了该文算法不仅能有效剔除目标旋转部件对逆合成孔径激光雷达成像的干扰,还能通过微多普勒特征的提取为目标识别提供新的途径。     

多站ISAR空间目标姿态估计方法

该文提出一种基于多站逆合成孔径雷达(ISAR)序列成像的空间目标姿态估计方法。方法提取各帧ISAR图像中目标的典型线性结构,结合目标轨道信息实现关键部件姿态估计。该文建立了较为稳健的空间目标ISAR几何结构分析流程,采用Radon变换对太阳能翼、平板天线等线性结构进行提取和关联,继而估计典型线性结构在距离-多普勒成像平面的姿态角变化,同时利用卫星轨道信息获得ISAR距离-多普勒投影矩阵进行线性结构的3维姿态解算,最终实现典型部件姿态的优化求解估计。仿真实验验证了所提算法可有效实现空间目标典型部件的姿态估计,同时利用多站ISAR观测数据可有效提升算法的估计精度。     

基于电磁散射模型的ISAR空中目标欺骗干扰方法

该文提出一种基于目标电磁散射模型的逆合成孔径雷达(ISAR)空中目标欺骗干扰算法,利用目标电磁散射模型对雷达回波进行调制,能够模拟遮挡、多次散射等目标散射特征,并包含目标的平动、姿态等运动特性,保证了虚假目标的逼真性。该算法计算量小,具有较强的实时性。通过仿真试验验证了欺骗干扰算法的有效性,并对算法的计算复杂性进行了分析。     

基于外辐射源的含旋转部件目标微动中心提取

针对基于外辐射源的无源雷达系统中,含旋转部件目标的微动中心位置不能够被有效提取这一问题,提出了一种基于逆Randon变换的微动中心提取方法。该方法首先利用子孔径综合成像方法对目标进行成像,然后结合已经获知的目标旋转部件的旋转频率、半径和初始相位信息,沿旋转部件的所有可能的旋转轨迹在子孔径综合成像的结果上进行逆Randon变换,然后通过提取逆Randon变换的峰值位置即可完成对旋转中心的提取。最后,仿真验证了该算法的有效性。     

基于分块图像统计特征的红外目标提取

提出了一种基于分块图像统计特征的红外目标提取方法,首先将图像逐步分成越来越小的块,根据块图像统计特征构造函数求其极大值,获得目标的种子区域和包含整个目标的约束区域;然后在约束区域内,将一种快速的区域生长方法用于目标种子区域的生长,最终提取出红外目标。通过对不同目标大小的红外飞机图像的实验,验证了算法的有效性。对算法在TI公司的DSP芯片TMS320VC33 150上实现的时间消耗进行了估算,结果表明可以达到实时提取目标的要求。     

双分支特征提取与循环细化的动态场景去模糊

针对现有的动态场景图像去模糊方法存在的特征提取不准确、未充分利用有效特征的问题,本文提出了一种基于双分支特征提取与循环细化的动态场景图像去模糊网络。整个网络包括特征提取网络、循环细化网络(cyclic refinement network, CRN)、图像重建(image reconstruction, IR)3部分。其中,特征提取网络包括模糊图像细节和轮廓特征(contour feature, CF)的提取,以残差单元作为特征提取网络的基本单元;循环细化网络通过交替融合轮廓特征和细节特征(detail feature, DF)来细化特征图,得到模糊图像的细化特征(refinement feature, RF);最后,在图像重建阶段,复用轮廓和细节特征,结合残差学习策略将轮廓特征、细节特征和细化后的特征逐级融合后通过非线性映射的方式重建清晰图像。在广泛使用的动态场景模糊数据集GOPRO上的实验结果表明,该方法的平均峰值信噪比(peak signal to noise ratio,PSNR)达到31.86,平均结构相似度(structure similarity,SSIM)达到0.947...     

On-line video object segmentation using illumination-invariant color-texture feature extraction and marker prediction

A novel on-line video object segmentation scheme based on illumination-invariant color-texture feature extraction and marker prediction is proposed in this paper. First, the location of the object of interest is initialized based on user-specified markers. Superpixels are generated in the next available frame of the input video to extract the illumination-invariant color-texture features of the object of interest. The proposed object marker prediction scheme consists of estimating the user-specified markers and locating the object of interest in the next available frame via superpixel motion prediction using illumination-invariant optical flow, marker superpixel candidate generation using short-term superpixel affinity, and maximum likelihood computation using long-term superpixel affinity. The experimental results obtained when the proposed method is applied to several challenging video clips demonstrate that the proposed approach is competitive with several other state-of-the-art methods, especially when the illumination and object motion change dramatically.     

Multi-level temporal feature fusion with feature exchange strategy for multiple object tracking

With the deepening of neural network research, object detection has been developed rapidly in recent years, and video object detection methods have gradually attracted the attention of scholars, especially frameworks including multiple object tracking and detection. Most current works prefer to build the paradigm for multiple object tracking and detection by multi-task learning. Different with others, a multi-level temporal feature fusion structure is proposed in this paper to improve the performance of framework by utilizing the constraint of video temporal consistency. For training the temporal network end-to-end, a feature exchange training strategy is put forward for training the temporal feature fusion structure efficiently. The proposed method is tested on several acknowledged benchmarks, and encouraging results are obtained compared with the famous joint detection and tracking framework. The ablation experiment answers the problem of a good position for temporal feature fusion.     

On wave modulation by a rotating object

When a time harmonic electromagnetic wave is incident upon a rotating object which is not rotationally symmetric about the axis of rotation, modulation in the secondary waves generally will occur. Two scattering and reflection problems where, under certain conditions, no modulation occurs, are discussed. In the first case, a transverse electric (TE) or transverse magnetic (TM) wave is incident upon an object inside a circular waveguide. The object is rotating about the axis of the waveguide and has periodic characterisitcs in the azimuthal direction with period2pi/N(N: an integer). In the second case, the waveguide is removed, and a linearly polarized plane wave is incident upon the object along its axis of rotation.     

Evolutionary feature synthesis for object recognition

Features represent the characteristics of objects and selecting or synthesizing effective composite features are the key to the performance of object recognition. In this paper, we propose a coevolutionary genetic programming (CGP) approach to learn composite features for object recognition. The knowledge about the problem domain is incorporated in primitive features that are used in the synthesis of composite features by CGP using domain-independent primitive operators. The motivation for using CGP is to overcome the limitations of human experts who consider only a small number of conventional combinations of primitive features during synthesis. CGP, on the other hand, can try a very large number of unconventional combinations and these unconventional combinations yield exceptionally good results in some cases. Our experimental results with real synthetic aperture radar (SAR) images show that CGP can discover good composite features to distinguish objects from clutter and to distinguish among objects belonging to several classes. The comparison with other classical classification algorithms is favorable to the CGP-based approach proposed in this paper.     

Kernel-based feature extraction with a speech technology application

Kernel-based nonlinear feature extraction and classification algorithms are a popular new research direction in machine learning. This paper examines their applicability to the classification of phonemes in a phonological awareness drilling software package. We first give a concise overview of the nonlinear feature extraction methods such as kernel principal component analysis (KPCA), kernel independent component analysis (KICA), kernel linear discriminant analysis (KLDA), and kernel springy discriminant analysis (KSDA). The overview deals with all the methods in a unified framework, regardless of whether they are unsupervised or supervised. The effect of the transformations on a subsequent classification is tested in combination with learning algorithms such as Gaussian mixture modeling (GMM), artificial neural nets (ANN), projection pursuit learning (PPL), decision tree-based classification (C4.5), and support vector machines (SVMs). We found, in most cases, that the transformations have a beneficial effect on the classification performance. Furthermore, the nonlinear supervised algorithms yielded the best results.     

PointNetV3:feature extraction with position encoding

Feature extraction of point clouds is a fundamental component of three-dimensional (3D) vision tasks. While existing feature extraction networks primarily focus on enhancing the geometric perception abilities of networks and overlook the crucial role played by coordinates. For instance, though two airplane wings share the same shape, it demands distinct feature representations due to their differing positions. In this paper, we introduce a novel module called position aware module (PAM) to leverage the coordinate features of points for positional encoding, and integrating this encoding into the feature extraction network to provide essential positional context. Furthermore, we embed PAM into the PointNet++ framework, and design a novel feature extraction network, named PointNetV3. To validate the effectiveness of PointNetV3, we conducted comprehensive experiments including classification, object tracking and object detection on point cloud. The results of remarkable improvement in three tasks demonstrate the exceptional performance achieved by PointNetV3 in point cloud processing.