基于改进ORB特征的遥操作工程机器人双目视觉定位

为了提高遥操作工程机器人定位系统图像处理的实时性,提出一种基于改进ORB特征的遥操作工程机器人双目视觉定位方法。利用图像二分法剔除掉图像中的无效区域,只保留匹配区域,采用ORB算法完成有效区域的匹配,最后采用RANSAC算法剔除伪匹配,得到较为精准的匹配点对。与传统算法对比实验结果表明,该方法可以提高匹配效率,消除误匹配,提高匹配精度,定位效率高,能满足遥操作工程机器人作业的实时性要求,可为遥操作工程机器人及其他领域遥操作机器人的视觉提示系统设计提供技术参考。     

基于直线Hough变换的图像配准方法

为了有效解决不同传感器、不同视角和不同时相条件的图像配准问题,提出了一种基于直线极坐标参数在Hough空间求解图像变换参数的图像配准算法。先提取图像中直线极坐标特征参数,形成匹配特征空间;然后在Hough空间逐步求解RST图像变换的旋转、尺度和平移参数;最后利用实际图像对算法的性能进行了分析与验证。实验结果表明,该方法不需进行复杂的匹配空间搜索,具有适应性强、配准精度高的优点。     

一种新的直线提取算法研究

研究了一种快速的图像直线提取算法。将边缘按方向划分成若干子边缘,利用判据从子边缘提取出局部直线,然后依据准则合并相应子边缘得到全局直线及参数。准确提取出图像中的直线特征及端点和方向等参数。实验结果表明,算法比Hough变换更准确、快速、可靠地提取图像的直线特征。     

基于模板搜索的高分辨率SAR图像机场提取方法

针对高分辨率SAR图像机场提取问题,设计了以尺度变换、边缘检测、短线提取、短线连接、平行线提取和验证识别等流程的机场提取方案,并针对机场跑道特点在短线提取和短线连接两个关键步骤上提出了新的算法。直线提取利用了边缘线的结构特征,将边缘曲线看成三种线基元的组合,能从边缘图像中快速拟合出短直线。短线连接提出了一种基于模板搜索的直线连接方法,将短直线连接问题转化为在模板参数空间里搜索峰值的问题。实验表明,本文方法简单快速可行。     

一种基于动态图像处理的邮件检测方法

利用动态图像处理技术,设计了一种实时处理的邮件检测算法。采用了一种快速的中值滤波算法进行降噪处理,提出了一种简洁的边界提取算法,可以快速地提取出单像素边界。然后以自适应多直线匹配的方法实现两帧图像的配准,并利用差分图像信息实现邮件图像的提取,最后计算出邮件的相关参数。仿真实验表明,该算法能有效检测出运动状态下邮件的相关参数,实时性良好。     

基于夹角的直线检测算法

为了能有效解决Hough变换计算量大、处理速度慢等问题,提出了一种基于夹角的直线提取算法.该算法直接在图像空间提取直线,通过判断图像中任意三点形成的直线夹角,获得一条可能的直线,然后再在数据空间中进一步判定这条直线的真实性.实验证明,该算法具有较高的直线检出率、检测精度和运行速度,与具有类似检出率的算法相比虚假直线数较少,综合性能具有优势.     

基于空间平行直线束的CCD摄像机内外参数标定

为提高计算机视觉检测中的摄像机标定算法的效率与稳定性,降低对标定设备的要求,提出了一种新的基于主动视觉的摄像机标定算法.在分析了空间平行直线束的中心投影规律的基础上标定摄像机内外参数.与以往方法不同,在标定过程中保持摄像机位置不动,通过控制标定模板沿具有直线边缘的物体作任意量值的平移运动来实现对摄像机内外参数的求解.利用焦线的直线约束对镜头畸变进行修正,有效地提高标定结果的精度.将内外参数标定分为3个独立的阶段分别进行,克服了整体求解过程中未知参数间的相关性影响.该方法原理简单,且不需要知道模板上的任何物理度量.模拟实验和真实图像实验结果表明了该方法的高精度和高稳定性.     

宽带图像信号的直线提取

该文用FPGA＋DSP实现了宽带图像信号的实时直线提取,适用于通常的视频图像信号和线阵CCD成像的连续图像信号。实现的直线提取模块已经用于高传输率的快速遥感图像处理系统。算法将直线提取中的参数计算分解为一个可以累加的过程,从而简化了计算,同时保证了直线参数的准确性,在理论上证明了算法的完备性,文章的最后给出了实验结果及比较。     

基于二次曲线的纯旋转摄像机自标定

研究探讨了一种基于平面二次曲线的纯旋转摄像机自标定方法.在不同的方位拍摄三幅或三幅以上图像,每幅图像至少包含两个空间平面二次曲线、或两个二次曲面、或一个平面二次曲线与一个二次曲面的投影,利用图像之间的二次曲线对应关系,可以确定摄像机的内参数矩阵,同时可以获得摄像机不同方位之间的旋转矩阵.由于使用的定标基元为二次曲线,是较点和直线包含更多信息的基元,因而基元之间的匹配容易自动实现,并有助于提高标定算法的鲁棒性和在线实时性.模拟实验和真实图像实验表明文中所介绍的方法是可行的.     

基于混合算法的空间机器人运动学参数辨识

外太空环境恶劣,空间遥操作机器人结构在太空环境作业时会产生形变,而且其加工生产也存在加工误差,空间遥机器人的形变引起DH参数的误差,为了完成空间机器人系统的地而仿真预测,并且确保空间遥操作机器人完成工作任务,必须根据遥测数据准确的辨识出空间机器人系统的运动学参数.提出了混合非线性参数辨识的LM(Levenberg-Marquarat)和递推最小二乘办法的混合辨识算法.最后,给出了办法的实例仿真,说明了辨识算法的稳定性,能够完成对空间遥操作机器人的运动学参数的辨识.     

网络机器人控制系统图像摄入的新方法

摄像机—图像采集卡方法是网络机器人控制系统图像摄入的经典方式。然而,这种方法存在着成本偏高、应用不灵活等的弊端。本文基于TWAIN技术规范提出了一种新的独立USB摄像头方法,该方法在VC++环境下实现驱动通用数字图像设备USB摄像头,与经典方法相比,本方法在应用于诸如基于网络的遥操作机器人控制系统中实现了低成本、应用灵活。     

A New Method for Image Input in Internet-based Telerobotic Control System

1 Introduction Network robot, also named Internet- based telerobot , this technology is enjoying wider and wider application in a large variety of fields for its safety in handling, cost- effectiveness and great convenience in operation. It also plays an impetus role in lowering cost and labor in- tensity, raising productivity and accelerating the integra- tion, coordination process in the large- scale modern production. With its significant potential for economic profits, the Internet- based…     

Fitting conics to paracatadioptric projections of lines

The paracatadioptric camera is one of the most popular panoramic systems currently available in the market. It provides a wide field of view by combining a parabolic shaped mirror with a camera inducing an orthographic projection. Previous work proved that the paracatadioptric projection of a line is a conic curve, and that the sensor can be fully calibrated from the image of three or more lines. However, the estimation of the conic curves where the lines are projected is hard to accomplish because of the partial occlusion. In general only a small arc of the conic is visible in the image, and conventional conic fitting techniques are unable to accurately estimate the curve. The present work provides methods to overcome this problem. We show that in uncalibrated paracatadioptric views a set of conic curves is a set of line projections if and only if certain properties are verified. These properties are used to constrain the search space and correctly estimate the curves. The conic fitting is solved naturally by an eigensystem whenever the camera is skewless and the aspect ratio is known. For the general situation the line projections are estimated using non-linear optimization. The set of paracatadioptric lines is used in a geometric construction to determine the camera parameters and calibrate the system. We also propose an algorithm to estimate the conic locus corresponding to a line projection in a calibrated paracatadioptric image. It is proved that the set of all line projections is a hyperplane in the space of conic curves. Since the position of the hyperplane depends only on the sensor parameters, the accuracy of the estimation can be improved by constraining the search to conics lying in this subspace. We show that the fitting problem can be solved by an eigensystem, which leads to a robust and computationally efficient method for paracatadioptric line estimation.     

基于三条相互垂直直线的单目位姿估计

基于单目视觉的位姿估计是计算机视觉中的典型问题之一。文中利用目标物体上的三条相互垂直的直线特征和相机像平面上这些特征的对应获得已标定相机相对于目标物体的位姿参数,给出其闭式求解方法,并证明问题解的数量与相机光心和三条直线的相对位置有关。当光心位于两个特殊平面以外时存在唯一解,反之若在该两个平面之间则存在两个解,并且这两个解具有对称性,该性质可作为合理解的判别依据。由于三条相互垂直的直线是长方体的三条边缘,而长方体在现实世界中广泛存在,该结论为应用直线特征进行单目视觉位姿估计及合作目标设计提供理论依据。     

Deformation visual inspection of industrial parts with image sequence

A new approach to reconstructing and inspecting the deformation of industrial parts, especially sheetmetal parts based on CAD-designed data and hybrid point-line bundle adjustment with image sequence, is proposed. Nonmetric image sequence and CAD-designed data of parts are used as the source of information. The strategy of our approach is to reconstruct and inspect deformations of parts automatically with image points and line segments extracted from the images. Basic error equation of line photogrammetry and its modified form are addressed in detail. It is shown that when a certain proper weight is selected, adjustment by condition equations and adjustment by observation equations are equivalent for line photogrammetry. A novel hybrid point-line bundle adjustment algorithm is used to reconstruct industrial parts. The proposed hybrid adjustment model can be used in various 3D reconstruction applications of objects mainly composed of points and lines. The developed inspection system is tested with true image data acquired by a CCD camera, and the results are very satisfying.Received: 27 May 2002, Accepted: 18 September 2003, Published online: 8 June 2004     

A homotopy-based approach for computing defocus blur and affine transform simultaneously

This paper presents a homotopy-based algorithm for a simultaneous recovery of defocus blur and the affine parameters of apparent shifts between planar patches of two pictures. These parameters are recovered from two images of the same scene acquired by a camera evolving in time and/or space and for which the intrinsic parameters are known. Using limited Taylor's expansion one of the images (and its partial derivatives) is expressed as a function of the partial derivatives of the two images, the blur difference, the affine parameters and a continuous parameter derived from homotopy methods. All of these unknowns can thus be directly computed by resolving a system of equations at a single scale. The proposed algorithm is tested using synthetic and real images. The results confirm that dense and accurate estimation of the previously mentioned parameters can be obtained.     

Nonmetric calibration of wide-angle lenses and polycameras

Images taken with wide-angle cameras tend to have severe distortions which pull points towards the optical center. This paper proposes a simple method for recovering the distortion parameters without the use of any calibration objects. Since distortions cause straight lines in the scene to appear as curves in the image, our algorithm seeks to find the distortion parameters that map the image curves to straight lines. The user selects a small set of points along the image curves. Recovery of the distortion parameters is formulated as the minimization of an objective function which is designed to explicitly account for noise in the selected image points. Experimental results are presented for synthetic data as well as real images. We also present the idea of a polycamera which is defined as a tightly packed camera cluster. Possible configurations are proposed to capture very large fields of view. Such camera clusters tend to have a nonsingle viewpoint. We therefore provide analysis of what we call the minimum working distance for such clusters. Finally, we present results for a polycamera consisting of four wide-angle sensors having a minimum working distance of about 4 m. On undistorting the acquired images using our proposed technique, we create real-time high resolution panoramas.     

Geometric properties of central catadioptric line images and their application in calibration

In central catadioptric systems lines in a scene are projected to conic curves in the image. This work studies the geometry of the central catadioptric projection of lines and its use in calibration. It is shown that the conic curves where the lines are mapped possess several projective invariant properties. From these properties, it follows that any central catadioptric system can be fully calibrated from an image of three or more lines. The image of the absolute conic, the relative pose between the camera and the mirror, and the shape of the reflective surface can be recovered using a geometric construction based on the conic loci where the lines are projected. This result is valid for any central catadioptric system and generalizes previous results for paracatadioptric sensors. Moreover, it is proven that systems with a hyperbolic/elliptical mirror can be calibrated from the image of two lines. If both the shape and the pose of the mirror are known, then two line images are enough to determine the image of the absolute conic encoding the camera's intrinsic parameters. The sensitivity to errors is evaluated and the approach is used to calibrate a real camera.     

A robust hybrid image-based modeling system

This paper presents a new robust image-based modeling system for creating high-quality 3D models of complex objects from a sequence of unconstrained photographs. The images can be acquired by a video camera or hand-held digital camera without the need of camera calibration. In contrast to previous methods, we integrate correspondence-based and silhouette-based approaches, which significantly enhances the reconstruction of objects with few visual features (e.g., uni-colored objects) and improves surface smoothness. Our solution uses a mesh segmentation and charting approach in order to create a low-distortion mesh parameterization suitable for objects of arbitrary genus. A high-quality texture is produced by first parameterizing the reconstructed objects using a segmentation and charting approach, projecting suitable sections of input images onto the model, and combining them using a graph-cut technique. Holes in the texture due to surface patches without projecting input images are filled using a novel exemplar-based inpainting method which exploits appearance space attributes to improve patch search, and blends patches using Poisson-guided interpolation. We analyzed the effect of different algorithm parameters, and compared our system with a laser scanning-based reconstruction and existing commercial systems. Our results indicate that our system is robust, superior to other image-based modeling techniques, and can achieve a reconstruction quality visually not discernible from that of a laser scanner.     

Depth from Defocus Estimation in Spatial Domain

This paper presents an algorithm for a dense computation of the difference in blur between two images. The two images are acquired by varying the intrinsic parameters of the camera. The image formation system is assumed to be passive. Estimation of depth from the blur difference is straightforward. The algorithm is based on a local image decomposition technique using the Hermite polynomial basis. We show that any coefficient of the Hermite polynomial computed using the more blurred image is a function of the partial derivatives of the other image and the blur difference. Hence, the blur difference is computed by resolving a system of equations. The resulting estimation is dense and involves simple local operations carried out in the spatial domain. The mathematical developments underlying estimation of the blur in both 1D and 2D images are presented. The behavior of the algorithm is studied for constant images, step edges, line edges, and junctions. The selection of its parameters is discussed. The proposed algorithm is tested using synthetic and real images. The results obtained are accurate and dense. They are compared with those obtained using an existing algorithm.