行星陨石坑检测算法研究综述

陨石坑检测对于确定行星体的年代信息、行星探测和载人登月探测器的自动导航着陆具有着重要的参考意义。总结陨石坑检测方法,将传统视觉的陨石坑检测算法分为基于边缘、阴影和区域3个方面进行阐述;从数据集、网络结构和评价指标的角度,重点分析了深度学习陨石坑检测算法;针对目前深度学习领域的研究热点,对未来陨石坑检测算法提出发展方向。分析得出:深度学习陨石坑检测方法相比传统视觉的陨石坑检测方法更加高效,无需人工设计特征,检测精度显著提高。     

面向山地区域光照变化下的鲁棒景象匹配方法

提出了一种面向山地区域光照变化下的鲁棒景象匹配导航方法。该方法针对山区景象匹配导航中光照环境不同造成的基准图与实时图像不一致问题,采取在高程数据上使用光照模型生成光照明暗图,利用数字高程图(DEM)得到水流汇集数据并生成山谷显著图,将光照明暗图与山谷显著图融合作为基准图;针对基准图与实时图中细节边缘的差异带来的误匹配问题,提出了基于形态学约束的Hausdorff距离边缘匹配算法。采用LANDSAT图像与ASTERDEM高程数据进行实验分析,结果表明提出的方法匹配正确率高且鲁棒性好。     

基于双目视觉的管路快速检测技术研究与实现

为了改变传统管路检测方法的弊端,实现管路的实时快速测量,在研究双目视觉技术的基础上提出了将视觉测量应用于管路系统检测中,实现管路模型三维重建工作。首先采用双目摄像机,对管路系统进行拍摄,得到多组管路图像,然后利用相机的标定确定相机的内外参数,通过经典的边缘提取方法提取图像中的边缘特征,采用曲线拟合的方法提取管路的中心线,通过管路中心线匹配算法,建立了左右图像的匹配关系,最后得到管路的几何参数并进行三维重建。实例验证了该方法可行、有效。     

恶劣天气下的仿生偏振定向方法

针对偏振光导航在恶劣天气下精度显著下降的问题,提出了一种可以在恶劣天气下基于大气偏振模式的定向算法。与现有方法相比,首次将三维块匹配与canny边缘检测结合的思想应用于修复被不同天气破坏的偏振角度图像中。具体而言,将偏振角度图像的修复分为噪声粗处理和边缘提取处理去噪两部分。在噪声粗处理阶段采用三维块匹配算法,在边缘提取处理去噪部分,利用canny边缘检测算法对偏振角度图像进行二次去噪。实验结果表明,该方法不仅能够提高晴朗天空下的定向精度,而且能够显著提升在阴天、沙尘、雾霾等恶劣天气条件下的导航定向精度,即使在偏振角图像对称∞模式被破坏的情况下,航向角精度仍可由9.4470°提高到1.6859°。     

恶劣天气下的仿生偏振定向方法

针对偏振光导航在恶劣天气下精度显著下降的问题，提出了一种可以在恶劣天气下基于大气偏振模式的定向算法。与现有方法相比，首次将三维块匹配与canny边缘检测结合的思想应用于修复被不同天气破坏的偏振角度图像中。具体而言，将偏振角度图像的修复分为噪声粗处理和边缘提取处理去噪两部分。在噪声粗处理阶段采用三维块匹配算法,在边缘提取处理去噪部分，利用canny边缘检测算法对偏振角度图像进行二次去噪。实验结果表明，该方法不仅能够提高晴朗天空下的定向精度，而且能够显著提升在阴天、沙尘、雾霾等恶劣天气条件下的导航定向精度，即使在偏振角图像对称∞模式被破坏的情况下，航向角精度仍可由9.4470°提高到1.6859°。     

基于边缘相似性的异源图像匹配

异源图像匹配是视觉导航、多源图像融合分析的关键步骤之一。对于成像机理差别较大的异源图像,如SAR图像和可见光图像,采用传统的异源图像匹配算法难以得到满意结果。本文提出一种基于边缘相似性的异源图像匹配方法,首先分别提取待匹配图像的边缘特征点集;然后计算基准图的边缘距离场;最后基于边缘相似性模型,通过实时图边缘图和基准图边缘距离场计算边缘相似度,寻找相似度最大的变换参数即为最终匹配参数。采用SAR与可见光图对方法进行了测试,结果表明,这种方法能够快速可靠地实现异源图像匹配。     

基于力场转换理论的图像粗大边缘检测方法

基于粗大边缘的异源图像匹配在导航制导等领域具有广阔的应用前景,但是现有边缘检测方法很难提取出异源图像中的粗大边缘.根据异源图像成像原理和灰度分布特点,提出一种基于力场转换理论的异源图像粗大边缘检测新方法.首先,根据引力概念计算图像中各像素点受到合力的大小和方向;其次,为了去除光照和异源图像灰度不同的影响,对图像中像素点...     

图像模板测量技术在零件不规则薄圆孔检测中的应用

针对不规则薄圆孔的检测,提出了一种基于数字图像处理的模板匹配检测方法,运用数字图像处理技术对采集的圆孔图像进行截取、降噪、分割、边缘检测等处理,再把提取出的圆与标定模板上的标准圆进行比较,实现对不规则圆孔尺寸的检测,并通过实验证明了该方法的可行性和实用性。     

基于机器视觉的半导体表面缺陷检测研究

半导体的广泛应用使得人们对其质量要求越来越高。半导体生产过程中塑封表面缺陷的检测得到更多生产厂家的重视。本文对SOT-23封装式半导体的表面塑封缺陷进行了研究,改进并优化半导体质量缺陷检测系统,通过边缘检测算法提取半导体管体的塑封边缘,确定被检管体的位姿,缩小检测范围,使用基于边缘点的模板匹配算法来判断字符的完整性,最后利用差影法准确地检测出塑封缺陷。经工厂试用后,结果显示此系统能有效地检测出表面质量缺陷。目前此系统已在工厂正式使用。     

基于3D Zernike矩的巡检器与空间站的相对导航算法

针对航天器相对导航问题,以空间站表面为"特殊地形",提出一种基于大型航天器表面巡检的相对导航算法。首先,运用巡检飞行器上的TOF （Time of Flight）相机测量空间站表面局部点云数据,以该点云数据为实时图,以空间站表面先验点云数据为基准图。然后,利用3D Zernike矩与三维地形间的一一对应关系,将三维地形匹配转化为基于3D Zernike矩的特征向量匹配。在此基础上求解实时图与匹配上的基准图间的相对位置、相对姿态,从而确定两航天器间的相对导航参数,并通过实验分析了匹配精度及速度的主要影响因素。最后,将该相对导航参数与惯性系统推算的相对导航参数在扩展卡尔曼滤波器的框架下实现信息融合,估计了巡检飞行器与空间站间的相对位置、相对姿态,实验结果表明,相对位置精度优于0.002 m,相对姿态精度优于0.1°。     

Optimal crater landmark selection based on optical navigation performance factors for planetary landing

Planetary craters are natural navigation landmarks that widely exist and are easily observed. Optical navigation based on crater landmarks has become an important autonomous navigation method for planetary landing. Due to the increase in observed crater landmarks and the limitation of onboard computation, the selection of good crater landmarks has gradually become a research hotspot in the field of landmark-based optical navigation. This paper designs a fast crater landmark selection method, which not only considers the configuration observability of crater subsets but also focuses on the influence on navigation performance arising from the measurement uncertainty and the matching confidence of craters, which is different from other landmark selection methods. The factor of measurement uncertainty, which is anisotropic, correlated and nonidentically distributed, is quantified and integrated into selection based on crater pairing detection and localization error evaluation. In addition, the concept of the crater matching confidence factor is introduced, which reflects the possibility of 2D projection measurements corresponding to 3D positions. Combined with the configuration observability factor, the crater landmark selection indicator is formed. Finally, the effectiveness of the proposed method is verified by Monte Carlo simulations.     

Novel approach of crater detection by crater candidate region selection and matrix-pattern-oriented least squares support vector machine

Impacted craters are commonly found on the surface of planets, satellites, asteroids and other solar system bodies. In order to speed up the rate of constructing the database of craters, it is important to develop crater detection algorithms. This paper presents a novel approach to automatically detect craters on planetary surfaces. The approach contains two parts: crater candidate region selection and crater detection. In the first part, crater candidate region selection is achieved by Kanade-Lucas-Tomasi (KLT) detector. Matrix-pattern-oriented least squares support vector machine (MatLSSVM), as the matrixization version of least square support vector machine (SVM), inherits the advantages of least squares support vector machine (LSSVM), reduces storage space greatly and reserves spatial redundancies within each image matrix compared with general LSSVM. The second part of the approach employs MatLSSVM to design classifier for crater detection. Experimental results on the dataset which comprises 160 preprocessed image patches from Google Mars demonstrate that the accuracy rate of crater detection can be up to 88%. In addition, the outstanding feature of the approach introduced in this paper is that it takes resized crater candidate region as input pattern directly to finish crater detection. The results of the last experiment demonstrate that MatLSSVM-based classifier can detect crater regions effectively on the basis of KLT-based crater candidate region selection.     

Cooperative fault detection and recovery in the GNSS positioning of mobile agent swarms based on relative distance measurements

Relative measurements are exploited to cooperatively detect and recover faults in the positioning of Mobile Agent(MA) Swarms(MASs). First, a network vertex fault detection method based on edge testing is proposed. For each edge, a property that has a functional relationship with the properties of its two vertices is measured and tested. Based on the edge testing results of the network, the maximum likelihood principle is used to identify the vertex fault sources. Second, an edge distance testing...     

Bayesian edge detector for SAR imagery using discontinuity-adaptive Markov random feld modeling

Synthetic aperture radar（SAR）image is severely affected by multiplicative speckle noise,which greatly complicates the edge detection.In this paper,by incorporating the discontinuityadaptive Markov random feld（DAMRF）and maximum a posteriori（MAP）estimation criterion into edge detection,a Bayesian edge detector for SAR imagery is accordingly developed.In the proposed detector,the DAMRF is used as the a priori distribution of the local mean reflectivity,and a maximum a posteriori estimation of it is thus obtained by maximizing the posteriori energy using gradient-descent method.Four normalized ratios constructed in different directions are computed,based on which two edge strength maps（ESMs）are formed.The fnal edge detection result is achieved by fusing the results of two thresholded ESMs.The experimental results with synthetic and real SAR images show that the proposed detector could effciently detect edges in SAR images,and achieve better performance than two popular detectors in terms of Pratt＇s fgure of merit and visual evaluation in most cases.     

图像边缘提取的启发式搜索算法

常规的图像边缘提取方法容易受到噪声的影响,导致了大量不连续边缘的产生。本文试验了一种基于边缘分段自增强的启发式搜索(EdgeDetectionalgorithmbasedonHeuristicSearchED-HS)算法,该算法通过对边缘检测后图像的遍历搜索获得各种可能的边缘轨迹,然后对每条搜索轨迹进行分段自增强,最后根据增强程度的积累决定图像边缘。文中阐述和分析了算法的机理,并以加入了高斯噪声的“Lena图像”作为样本进行了计算验证。结果初步证明了该算法能够在较高的噪声条件下有效的提取到连续、清晰的边缘。     

一种基于边缘特征的背景差分运动目标检测方法

针对背景差分运动目标检测中目标边缘不够精确的问题,提出一种基于边缘特征的背景差分运动目标检测方法.该方法结合了均值背景的总体特性和对称帧差的实时性.首先,利用包含同一图像的两幅对称帧差相与结果获取运动目标的准确边缘,并将其作为目标分割的边界限制;然后,利用背景差分方法获取运动目标区域范围,提取目标像索点作为区域生长的种...     

Expectations for Crater Size and Photometric Evolution from the Deep Impact Collision

The NASA Discovery Deep Impact mission involves a unique experiment designed to excavate pristine materials from below the surface of comet. In July 2005, the Deep Impact (DI) spacecraft, will release a 360 kg probe that will collide with comet 9P/Tempel 1. This collision will excavate pristine materials from depth and produce a crater whose size and appearance will provide fundamental insights into the nature and physical properties of the upper 20 to 40 m. Laboratory impact experiments performed at the NASA Ames Vertical Gun Range at NASA Ames Research Center were designed to assess the range of possible outcomes for a wide range of target types and impact angles. Although all experiments were performed under terrestrial gravity, key scaling relations and processes allow first-order extrapolations to Tempel 1. If gravity-scaling relations apply (weakly bonded particulate near-surface), the DI impact could create a crater 70 m to 140 m in diameter, depending on the scaling relation applied. Smaller than expected craters can be attributed either to the effect of strength limiting crater growth or to collapse of an unstable (deep) transient crater as a result of very high porosity and compressibility. Larger then expected craters could indicate unusually low density (< 0.3 g cm⁻³) or backpressures from expanding vapor. Consequently, final crater size or depth may not uniquely establish the physical nature of the upper 20 m of the comet. But the observed ejecta curtain angles and crater morphology will help resolve this ambiguity. Moreover, the intensity and decay of the impact “flash” as observed from Earth, space probes, or the accompanying DI flyby instruments should provide critical data that will further resolve ambiguities.