水下目标亮点拓扑特征提取及自动识别方法

针对水下目标逆合成孔径声呐(Inverse Synthetic Aperture Sonar,ISAS)图像识别问题中观测角度随机多变,目标结构相互遮挡问题,提出一种基于多亮点拓扑矢量特征的ISAS水下目标识别方法。通过分析ISAS成像过程中散射点位置由三维空间向二维成像平面的投影关系,表明了横向定标后的声呐图像中强亮点之间的距离仅由目标散射结构之间的物理距离决定,据此基于强亮点之间的相互距离,构造能稳定描述不同观测角度下目标的拓扑矢量特征。然后通过K-means聚类获取多聚类中心以克服目标结构互相遮挡造成的亮点缺失问题。最终采用最近邻分类器实现目标识别。水池缩比模型实验表明,该方法对于水下目标的识别率达到84.0%。      

基于Stokes矢量的实时偏振差分水下成像研究

偏振差分水下成像能够有效地克服光散射效应造成的图像退化问题, 在水下物体探测与识别领域具有重要应用价值. 传统的偏振差分方法靠光学检偏器的无规则机械转动来实现对散射背景的共模抑制, 限制了其在水下成像过程中的实时探测性能. 本文通过分析偏振差分探测原理来建立偏振差分成像模型, 从理论上提出了基于Stokes矢量的计算偏振差分水下实时成像系统, 并进行了实验验证. 研究结果表明, 基于Stokes矢量的计算偏振差分成像不仅与传统的偏振差分方法具有相同的水下探测效果, 更重要的是可以实现快速成像过程. 该方法可以应用到目前的偏振成像仪器系统, 实现无需人-机互动的自动化实时偏振差分水下成像, 进一步提高水下物体探测与识别的效率.     

点云投影结合轻量化卷积神经网络实现三维成像声呐快速目标分类*

三维成像声呐的成像结果是三维点云,基于点云的三维成像声呐目标分类方法具有网络结构复杂,计算量大的特点,针对这一问题本文提出了一种将三维成像声呐成像结果从三维点云投影至二维图像的方法,并且使用轻量化卷积神经网络实现了三维成像声呐快速目标分类。该方法首先对三维成像声呐波束形成后的波束域数据进行最大值滤波和阈值滤波,降低点云数据维度;接着,依据三维成像声呐的波束方向,将点云投影为深度图和强度图,分别保存点云的位置信息和强度信息;然后,利用深度图和强度图分别作为第一个通道和第二个通道构建混合通道图,将混合通道图作为目标分类网络的输入,从而将三维点云的目标分类问题转换为二维图像的目标分类问题;最后使用MobileNetV2网络实现了三维成像声呐快速目标分类。实验结果表明,通过本文提出的投影方法可以用二维图像分类网络完成三维成像声呐点云的目标分类任务;而且混合通道图比单独的强度图和深度图收敛速度更快,结合目标识别网络可以25fps实时的进行目标分类,在真实数据集上分类精度达到了91.13%。     

一种新的激光车辙深度测量方法研究

车辙深度测量通常使用共梁式多路激光测距传感器测量路面多个离散点,由多个测量点组成的断面信息计算车辙深度,因横向采样点间距宽,导致测量误差较大。提出了一种新的激光车辙深度测量方法,采用线激光器和三维(3D)相机组合集成测量路面3D断面,通过3D断面解算车辙深度。3D相机以一定夹角采集激光器投射在路面的线结构光图像,获取路面的3D断面数据,对断面数据通过拉依达准则进行异常值剔除,再进行旋转、平移和模型识别,最终计算路面左右轮迹和最大车辙深度。实际证明,数据重复性和相关性都达到98%以上,与传统方法相比较,该方法采样间距小、测量精度高、成本低、通用性强,具有广阔的使用推广价值。     

基于光谱角时序不变性的红外目标识别

为了识别空间目标与气球诱饵,提出了基于光谱角时序不变性的红外目标识别方法。通过分析证实了空间目标与气球诱饵在温度时变特性上存在差异。为了反映目标测量功率温度时变本质,消除传感器与目标距离以及等效投影面积的时变耦合对测量功率的影响,提出了利用时序光谱角作为光谱向量的时序变化量度。该量度能够刻画光谱曲线的时序变化,反演物体温度时变特性,可以作为温度时变特性不同的目标和诱饵之间聚类识别的有效判据。仿真结果表明：该方法能够有效识别空间目标与气球诱饵;通过融合时序光谱特征,为空间目标识别提供了一种新的机制。     

Performance-enhanced recognition of a far and partially occluded 3-D object by use of direct pixel-mapping in computational curving-effective integral imaging

In this paper, we propose a novel approach to enhance the recognition performance of a far and partially occluded three-dimensional (3-D) target in computational curving-effective integral imaging by using the direct pixel-mapping (DPM) method. With this scheme, the elemental image array (EIA) originally picked up from a far and partially occluded 3-D target can be converted into a new EIA just like the one virtually picked up from a target located close to the lenslet array. Due to this characteristic of DPM, resolution and quality of the reconstructed target image can be highly enhanced, which results in a significant improvement of recognition performance of a far 3-D object. In addition, the computational time required for reconstruction of a far 3-D target could be also reduced because the distance between the lenslet array and image plane is virtually shortened in the new EIA transformed by DPM. Experimental results reveal that image quality of the reconstructed target image and object recognition performance of the proposed system have been improved by 1.75 dB and 4.56% on the average in PSNR (peak-to-peak signal-to-noise ratio) and NCC (normalized correlation coefficient), respectively, compared to the conventional system.     

一种基于特征点间线段倾角的姿态测量方法

基于目标特征点间线段倾角信息,提出了一种适合于目标远距离成像和相机内参未知条件下解算目标姿态的目标3维姿态测量方法.采用仿真图像对该方法的正确性进行了验证.实验结果:姿态测量误差绝对值均值小于0.6°,且目标成像尺寸为350pixel时,姿态测量误差绝对值小于0.5°.实验表明该算法具有较高解算准确度和较强的收敛性.     

Model-based light stripe detection for indoor navigation

Light stripe projection (LSP) is one of the most robust 3D recognition methods, and the general method of light stripe feature (LSF) detection is Laplacian of Gaussian (LOG) filtering. If distances to objects are various, as in the case of indoor navigation, LSF width becomes various according to distance. As the window size of spatial filtering influences the performance significantly, various LSF widths disturb LOG-based LSF detection with constant base length, that is constant window size. The irradiance maps of LSFs were reconstructed by high dynamic range imaging (HDRi) while changing the distance. By analyzing the irradiance maps, LSF irradiance map was modeled as a 2D Gaussian function whose parameters were approximated as functions of distance. After deriving LSF width function of distance, it was transformed into LSF width function of pixel coordinates by one-to-one relation between distance and y coordinates in LSP. The LSF width function can provide proper base length to LOG filtering. A self-calibration procedure is proposed which can estimate the parameters of LSF width function with only several images captured at new environment. Experimental results show that proposed model-based LSF detection overcomes normal LOG-based LSF detection.     

Three-dimensional recognition of occluded objects by using computational integral imaging

We have proposed a method to recognize partially occluded three-dimensional (3D) objects by using 3D volumetric reconstruction integral imaging (II). An II system captures multiple perspectives of occluded objects by using a microlens array. The reconstruction of the occluded 3D scene and target recognition are done digitally to reduce the effects of the occlusion. To verify system performance, we have implemented an optimum filter for object recognition. Both two-dimensional (2D) images and 3D II volumetric reconstructed images are considered. The correlation results of occluded 3D images for volumetric reconstruction show substantial improvements compared with those for conventional 2D imaging of occluded images.     

Three-dimensional integral imaging with improved visualization using subpixel optical ray sensing

In this Letter, we propose an improved three-dimensional (3D) image reconstruction method for integral imaging. We use subpixel sensing of the optical rays of the 3D scene projected onto the image sensor. When reconstructing the 3D image, we use a calculated minimum subpixel distance for each sensor pixel instead of the average pixel value of integrated pixels from elemental images. The minimum subpixel distance is defined by measuring the distance between the center of the sensor pixel and the physical position of the imaging lens point spread function onto the sensor, which is projected from each reconstruction point for all elemental images. To show the usefulness of the proposed method, preliminary 3D imaging experiments are presented. Experimental results reveal that the proposed method may improve 3D imaging visualization because of the superior sensing and reconstruction of optical ray direction and intensity information for 3D objects.     

Automated inspection of micro-defect recognition system for color filter

This study focused on micro-defect recognition and classification in color filters. First, six types of defects were examined, namely grain, black matrix hole (BMH), indium tin oxide (ITO) defect, missing edge and shape (MES), highlights, and particle. Orthogonal projection was applied to locate each pixel in a test image. Then, an image comparison was performed to mark similar blocks on the test image. The block that best resembled the template was chosen as the new template (or matching adaptive template). Afterwards, image subtraction was applied to subtract the pixels at the same location in each block of the test image from the matching adaptive template. The control limit law employed logic operation to separate the defect from the background region. The complete defect structure was obtained by the morphology method. Next, feature values, including defect gray value, red, green, and blue (RGB) color components, and aspect ratio were obtained as the classifier input. The experimental results showed that defect recognition could be completed as fast as 0.154 s using the proposed recognition system and software. In micro-defect classification, back-propagation neural network (BPNN) and minimum distance classifier (MDC) served as the defect classification decision theories for the five acquired feature values. To validate the proposed system, this study used 41 defects as training samples, and treated the feature values of 307 test samples as the BPNN classifier inputs. The total recognition rate was 93.7%. When an MDC was used, the total recognition rate was 96.8%, indicating that the MDC method is feasible in applying automatic optical inspection technology to classify micro-defects of color filters. The proposed system is proven to successfully improve the production yield and lower costs.     

基于多亮点分布的水下目标特征识别（英文）

An algorithm for underwater target feature recognition is proposed using its highlights distribution.For an underwater target with large size and slender body,it is assumed that the heading course and the length of the target are both determined by the distribution of its highlights.By supposing that these highlights obey Gaussian mixture distribution,the feature recognition problem can be transformed into a clustering problem.Therefore,using the collinearly constrained expectation maximization algorithm,the clustering centers of these highlights can be calculated and then the estimation of the heading and length of the target can be obtained with high accuracy.The effectiveness of the proposed method is demonstrated using simulations.     

实现均匀照明的LED系统设计方法

针对医用无影灯的应用要求,提出了一种利用非球面透镜实现对目标平面均匀照明的方法。基于能量守恒定律得到光源出射角与目标面之间的关系,利用Zemax的宏语言编写优化操作数使透镜优化满足上述关系,在非序列模式中对结果进行模拟和优化,并分别对透镜的前表面三种情况进行模拟,提出并模拟了LED球面阵列,并分析了角度及距离的偏移对照明均匀度的影响。结果表明,1m距离处实现了直径为25cm的平面内的均匀照明,均匀度(平均照度/最大照度)达到96%以上;球面阵列的设计可以满足无影灯的光分布要求,照明深度达到1m。     

基于快速轮廓转动力矩特征的激光主动成像目标识别

针对激光主动成像的图像特性,提出一种基于快速轮廓转动力矩的目标识别方法。将转动力矩的概念引入目标识别中,提出的快速轮廓转动力矩特征(FCTF)不仅包含了轮廓的尺寸、位置、规则度以及目标的亮暗等信息,同时对于旋转、尺度缩放等变换具有不变性。采用转动力矩的快速计算方法,提高了识别算法的计算效率。识别算法首先使用最大稳定极值区域(MSER)算法检测出目标特征区域,并将其变换为圆形区域,然后结合快速转动力矩特征算法提取出目标区域的局部不变特征,最后输入训练好的支持向量机分类器进行识别。实验结果表明相比于已有的激光主动成像目标识别方法,所提算法对于旋转、仿射变换均具有更高的识别率,同时单帧平均运算时间为9.68 ms,满足激光主动成像目标识别系统实时性的要求。     

Application of a Passive Polarimetric Infrared Sensor in Improved Detection and Classification of Targets

Automatic detection and recognition of targets by means of passive IR sensors suffer from limitations due to lack of sufficient contrast between the targets and their background, and among the facets of a target.In this paper the results of a suite of polarization-sensitive automatic target detection and recognition algorithms on sets of simulated and real polarimetric IR imagery are presented. A custom designed Polarimetric IR (PIR) imaging sensor is used for collecting real polarimetric target data-three of the four Stokes parameters under a variety of conditions. Then a set of novel algorithms are designed and tested that uses the target and background Stokes parameters for detection, segmentation and classification of targets.The empirical performance results are obtained in terms of the probabilities of detection, false alarm rate, segmentation accuracy, and recognition probabilities as functions of number of pixels on target, aspect and depression angles and under several background conditions (clutter densities) on the polarimetric and non-polarimetrirc data. These results show that a noticeable improvement over the non-polarimetric ATR can be achieved.     

Spin-image surface matching based target recognition in laser radar range imagery

We explore the problem of in-plane rotation-invariance existing in the vertical detection of laser radar (Ladar) using the algorithm of spin-image surface matching. The method used to recognize the target in the range imagery of Ladar is time-consuming, owing to its complicated procedure, which violates the requirement of real-time target recognition in practical applications. To simplify the troublesome procedures, we improve the spin-image algorithm by introducing a statistical correlated coefficient into target recognition in range imagery of Ladar. The system performance is demonstrated on sixteen simulated noise range images with targets rotated through an arbitrary angle in plane. A high efficiency and an acceptable recognition rate obtained herein testify the validity of the improved algorithm for practical applications. The proposed algorithm not only solves the problem of in-plane rotation-invariance rationally, but also meets the real-time requirement. This paper ends with a comparison of the proposed method and the previous one.     

基于压缩感知的三维物体成像的简单计算方法

从压缩感知的原理入手,阐述了基于压缩感知的三维物体成像方法。为解决压缩感知三维物体成像计算量大的问题,重点提出了一种三维信息计算的简单方法。此方法通过两次压缩感知计算就可得到位于多个距离处的物体的三维信息,大大减少了计算量。对此方法进行了数值模拟,并分析了采样率的提高对于距离计算精度的影响;建立实际的三维成像系统,实验结果证明了这种方法的可行性。     

具有终端角度约束的自主水下航行器鲁棒制导律（英文）

Based on robust control design method,a variable structure guidance method is proposed for autonomous underwater vehicle(AUV) during the guiding course with terminal impact angle constraint.Considering the intercept geometry,a sliding mode controller is proposed for controlling the hne of sight angle rate and the impact angle,based on the principle which controls the line of sight angle rate to approach zero and the terminal angle to approach the expected value more quickly as the distance decreases.Simulation results show that,with the application of the proposed method,small miss distance is achieved and the expected impact angle is reached.In addition,the system is robust to the target maneuvering.     

激光红外主被动复合导引系统

提出了采用激光主动三维成像技术配合被动红外成像技术共同工作的复合导引体制,用于提升地对地导弹的作战效能及对于隐身目标的识别能力。给出了各分系统的设计方案,并提出了合理的导引策略。该套系统能够兼顾红外大视场搜索及激光小视场三维成像,丰富的目标图像信息更加有利于对作战目标进行准确识别。整套复合光学导引系统结构简单、加工难度适中,在将整套导引系统口径控制在100 mm左右的情况下,同样能够实现4 km以上距离的导引。该项技术的提出对于我国复合导引技术的发展及我军导弹作战能力的提升有着重要意义。     

Investigation of composite electromagnetic scattering from ship-like target on the randomly rough sea surface using FDTD method

Composite electromagnetic scattering from a two-dimensional (2D) ship-like target on a one-dimensional sea surface is investigated by using the finite-difference time-domain (FDTD) method. A uniaxial perfectly matched layer is adopted for truncation of FDTD lattices. The FDTD updated equations can be used for the total computation domain by choosing the uniaxial parameters properly. To validate the proposed numerical technique, a 2D infinitely long cylinder over the sea surface is taken into account first. The variation of angular distribution of the scattering changing with incident angle is calculated. The results show good agreement with the conventional moment method. Finally, the influence of the incident angle, the polarization, and the size of the ship-like target on the composite scattering coefficient is discussed in detail.