基于同心圆合成图像匹配的双目视觉标定

分析了双目视觉传感器的数学模型,提出了一种基于同心圆合成图像匹配的双目视觉传感器的标定方法。在测量范围内任意多次摆放同心圆靶标,由两台摄像机拍摄靶标图像。根据摄像机模型与已知同心圆在靶标坐标系上的位置关系,构造合成图像,将合成图像与观测图像进行相似度匹配,通过优化定位得到靶标上每个圆的圆心点图像坐标。利用左右图像对应的圆心图像坐标和双目视觉的约束关系,对双目视觉传感器参数进行非线性优化,并得到最优解。所提出的标定方法是在张正友方法的理论基础上,利用了图像的整体性进行的优化。实验结果表明,该方法提高了标定精度。     

A spatial calibration method for master-slave surveillance system

The master-slave surveillance system uses stationary-dynamic camera assemblies to achieve wide-area surveillance and selective focus-of-interest. In such a system, a stationary fish-eye camera monitors a panoramic field of environment from a distance, while a dynamic PTZ (Pan–Tilt–Zoom) dome camera is commanded to acquire high-resolution images from a focused direction and provide multi-scale zoomed-in information. In order to achieve the precise interaction, pre-processing spatial calibration between these two cameras is required. This paper introduces a novel vision based calibration approach to automatically calculate a transformation matrix model between the fish-eye coordinate system and the PTZ dome coordinate system by matching feature points in the scene. The experiment has demonstrated the effectiveness of using this method with high accuracy in short calibration time.     

A calibration method for stereo vision sensor with large FOV based on 1D targets

Large FOV (field of view) stereo vision sensor is of great importance in the measurement of large free-form surface. Before using it, the intrinsic and structure parameters of cameras should be calibrated. Traditional methods are mainly based on planar or 3D targets, which are usually expensive and difficult to manufacture especially for large dimension ones. Compared to that the method proposed in this paper is based on 1D (one dimensional) targets, which are easy to operate and with high efficiency. First two 1D targets with multiple feature points are placed randomly, and the cameras acquire multiple images of the targets from different angles of view. With the fixed angle between vectors defined by the two 1D targets we can establish the objective function with intrinsic parameters, which can be later solved by the optimization method. Then the stereo vision sensor with two calibrated cameras is set up, which acquire multiple images of another 1D target with two feature points in unrestrained motion. The initial values of the structure parameters are estimated by the linear method for the known distance between two feature points on the 1D target, while the optimal ones and intrinsic parameters of the stereo vision sensor are estimated with non-linear optimization method by establishing the minimizing function involving all the parameters. The experimental results show that the measurement precision of the stereo vision sensor is 0.046 mm with the working distance of about 3500 mm and the measurement scale of about 4000 mm×3000 mm. The method in this paper is proved suitable for calibration of stereo vision sensor of large-scale measurement field for its easy operation and high efficiency.     

基于光学参考棒的立体视觉测量系统现场标定技术

为实现大空间复杂工件的准确测量,精确标定立体视觉系统变得越来越重要。为了克服传统立体摄像机标定过程繁复、户外实现困难的弱点,提出了一种基于光学参考棒的灵活、有效的立体视觉测量系统标定技术。参考棒水平和深度方向各有三个距离已知的红外LED作为特征点。通过在测量范围内的不同位置和方位移动光学参考棒,两像机同时捕获参考棒上特征点的图像。基于匹配的特征像点以及对极线约束,利用线性算法和Levenberg-Marquardt(LM)迭代算法快速地标定立体视觉测量系统。两像机之间平移量的比例因子由参考棒上特征点间的已知距离确定。参量标定过程中,自动地控制光强,优化曝光时间,使不同位置处光点图像的强度均一致,可以获得高的信噪比,提高标定精度。实验结果表明,该方法灵活、有效,在线标定能达到很高的精度,将现场标定过程应用到实际的大空间三维测量系统中,测量最大误差为0.18 mm。     

三目自适应权值立体匹配和视差校准算法

立体匹配是计算机视觉研究中的关键问题.相比于双目视觉,三目视觉能够获得更多的信息和额外的极线约束消除立体匹配的歧义性.为了提高三目立体匹配的精度,提出一种基于自适应权值和视差校准的三日立体匹配方法.将双目视觉中有效的自适应权值窗选择算法应用到三目视觉中,进行匹配窗的选择;提出一种新的目标图像选择算法,能够合理利用平行基线三目立体视觉系统中不同目标图像提供的信息,有效地消除遮挡,提高匹配的精度;提出一种适用于三目视觉的视差校准算法,利用三目图像像素间的色彩相似性和距离约束将初始匹配的视差结果进行校准,得到最终的视差图.实验结果表明,本文算法结构简单,能够生成浓密、高精度的视差图.     

Constructing feature points for calibrating a structured light vision sensor by viewing a plane from unknown orientations

To calibrate a structured light vision sensor, it is necessary to obtain at least four non-collinear feature points that fall on the light stripe plane. We propose a novel method to construct non-collinear feature points used for calibrating a structured light vision sensor with a planar calibration object. After the planar calibration object is moved freely in the range of measuring of the structured light vision sensor at least twice, all the local world coordinates of the feature points falling on the light stripe plane can be readily obtained in site. The global world coordinates of the non-collinear feature points in the local world coordinate frame can be computed through the three-dimensional (3D) camera coordinate frame. A planar calibration object is designed according to the proposed approach to provide accurate feature points. The experiments conducted on a real structured light vision sensor that consists of a camera and a single-light-stripe-plane laser projector reveal that the proposed approach has high accuracy and is practical in the vision inspection applications. The proposed approach greatly reduces the cost of the calibration equipment and simplifies the calibrating procedure. It advances structured light vision inspection one step from laboratory environments to real world use.     

Novel calibration method for non-overlapping multiple vision sensors based on 1D target

The global calibration of multiple vision sensors (MVS) with non-overlapping views has been widely studied. In this paper, a novel calibration method for MVS with non-overlapping fields of view based on 1D target is presented. First, two neighboring vision sensors are selected. The rotation matrix between the two vision sensors is computed using the co-linearity property of the feature points on 1D target. Then the translation vector is computed according to the known distances between feature points on 1D target. The global calibration of all vision sensors is realized by repeating the above pair-wise calibration on different pairs of vision sensors. Due to the small volume and mobility of 1D target, the proposed global calibration method can be applied to vision sensors distributed in a large area or narrow space. Experiment results show that the RMS error of global calibration is within 0.060 mm.     

Self-calibration of multi-camera networks without feature correspondence between different cameras

An automatic calibration approach for multi-camera networks is proposed to calibrate the intrinsic parameters of each camera and the extrinsic parameters between different cameras. Firstly, the moving objects are tracking, and the feature points are detected and calculated by a matching method from image sequences. And then we estimate the intrinsic parameters of each camera respectively by a self-calibration method from the motion of feature points, while estimating the rotation and translation of each camera with respect to the object. Thirdly, we estimate the extrinsic parameters between different cameras from the rotation and the motion of each camera with respect to the object. Our method only needs to track the motion of objects in each camera without the correspondence between different cameras. It avoids the difficulty of the correspondence between different cameras in real networks. Experiments with simulated data and real images are carried out to verify the theoretical correctness and numerical robustness.     

Calibration for stereo vision system based on phase matching and bundle adjustment algorithm

Calibration for stereo vision system plays an important role in the field of machine vision applications. The existing accurate calibration methods are usually carried out by capturing a high-accuracy calibration target with the same size as the measurement view. In in-situ 3D measurement and in large field of view measurement, the extrinsic parameters of the system usually need to be calibrated in real-time. Furthermore, the large high-accuracy calibration target in the field is a big challenge for manufacturing. Therefore, an accurate and rapid calibration method in the in-situ measurement is needed. In this paper, a novel calibration method for stereo vision system is proposed based on phase-based matching method and the bundle adjustment algorithm. As the camera is usually mechanically locked once adjusted appropriately after calibrated in lab, the intrinsic parameters are usually stable. We emphasize on the extrinsic parameters calibration in the measurement field. Firstly, the matching method based on heterodyne multi-frequency phase-shifting technique is applied to find thousands of pairs of corresponding points between images of two cameras. The large amount of pairs of corresponding points can help improve the accuracy of the calibration. Then the method of bundle adjustment in photogrammetry is used to optimize the extrinsic parameters and the 3D coordinates of the measured objects. Finally, the quantity traceability is carried out to transform the optimized extrinsic parameters from the 3D metric coordinate system into Euclid coordinate system to obtain the ultimate optimal extrinsic parameters. Experiment results show that the procedure of calibration takes less than 3 s. And, based on the stereo vision system calibrated by the proposed method, the measurement RMS (Root Mean Square) error can reach 0.025 mm when measuring the calibrated gauge with nominal length of 999.576 mm.     

基于圆结构光视觉传感器的标定特征点获取方法

管道作为工业生产重要的传输手段其内表面腐蚀程度和瑕疵的精确检测对于保证安全生产具有重要意义。针对管道内表面圆结构光视觉检测,提出了一种基于共面参照物获取圆结构光视觉传感器标定特征点的新方法。该方法设计了圆结构光平面靶标,基于交比不变原理,以摄像机三维坐标系为中介,将多个局部世界坐标系下的标定特征点统一到全局世界坐标系中,得到位于圆结构光曲面上的非共线标定特征点的三维世界坐标。该方法降低了标定设备的成本,简化了结构光视觉传感器的标定过程。标定实验精度达到0.340 mm,标定结果表明,该方法切实可行。     

双目视觉用于鱼苗尺寸测量

为了有效地提高鱼苗尺寸测量的效率及精度,搭建了平行式双目立体视觉系统。根据双目视觉原理,首先基于改进后的由多组同心圆构成的标定板对双目视觉测量系统进行定标;然后利用Harris角点提取算法获取鱼苗图像的关键特征点,并基于归一化互相关(Normalized Cross Correlation,NCC)立体匹配算法对关键特征点进行匹配,提取坐标数据;最后根据坐标数据进行计算,得到鱼苗的空间坐标,实现对鱼苗尺寸的精确测量。结果表明,由所搭建的平行式双目立体视觉系统测量的相对误差在8%以内,为双目视觉应用于鱼类养殖业的可行性提供了依据。     

一种无相机标定的立体图像对校正新方法

双目立体视觉是光学被动三维测量的芷要方法。为了快速、准确地寻找对应点,通常要将立体图像对进行校正,消除垂直视差。提出了一种无需标定相机的立体图像对校正方法。该方法从基本矩阵计算初始透视投影、旋转和竖直平移变换矩阵．然后以对应点坐标为基础对这些变换矩阵进行优化计算,从而有效地避免了优化计算的局部最小值,而且不过分依赖基本矩阵的计算精度。通过对提出的方法和完全基于基本矩阵的图像校正方法以及无需基本矩阵计算的图像校正方法进行实验比较,结果表明提出的方法图像校正速度快,能有效地消除垂直视差,而产生的图像变形较小。     

一种极线近似的双目结构光相位立体匹配方法北大核心CSCD

针对双目结构光三维重建中的相位立体匹配效率较低问题,提出了一种极线近似的快速匹配方法。首先依据两相机光心与左像素形成平面与右成像平面交线对极线进行描述;对每行像素中部分区域的对应极线进行近似,结合立体视觉的连续性约束,使得孤立的沿各自极线搜索匹配相位改为区域内沿近似极线连续搜索匹配相位;同时结合双目相机位姿特性,实现全局均匀分区,避免针对每行数据重复分区;计算过程中采用查表法辅助计算。实验结果表明,立体匹配后获得点云平均误差为0.436 mm,属可接受误差范围内,立体匹配计算速度平均提升10.18倍,对640×480尺寸图像可在17 ms内完成立体匹配,可应用于结构光实时三维重建。     

A novel 1D target-based calibration method with unknown orientation for structured light vision sensor

The problem associated with calibrating a structured light vision sensor is that it is difficult to obtain the coordinates of the world calibration points falling on the light stripe plane. In this paper, we present a novel method to address this problem by randomly moving a 1D (one-dimension) target within the sensor's view field. At each position where the target is set, the world coordinates with one calibration point on the light stripe plane that can be obtained based on at least three preset known points on the 1D target by a proposed two-stage technique. Thus, as long as the 1D target is at least set at three different positions, not less than three such calibration points can be obtained to perform the structured light vision sensor calibration. The simulation and real experiments conducted reveal that the proposed approach has an accuracy of up to 0.065 mm. The advantages of the proposed method are: (1) 1D target is easily machined with high accuracy, which reduces the cost of the calibration equipment; (2) the method simplifies the calibration operation and can be convenient in on-site calibration; (3) the method is suitable for use in confined spaces.     

逆向工程中基于共轴立体视觉的曲面边界测量

针对逆向工程中引导性曲面边界信息的快速获取问题,系统地研究了共轴立体视觉测量方法,建立该方法的数学模型,详细分析了摄像机焦距、基线距等系统结构参数及被测点空间位置对测量精度的影响,通过数学分析确定摄像机基线距的最佳取值范围,研究共轴立体视觉测量系统特殊的极线几何关系.提出基于共轴立体视觉的曲面边界快速测量方法,利用三坐标测量机的精密机械系统及精确的空间定位能力,用单个摄像机以两次共轴定位摄取图像的方式实现共轴立体视觉测量功能,然后利用共轴立体视觉外极线相互平行且通过各自像平面主点的特殊极线几何关系简化同源像点匹配过程,从而快速获取被测曲面的边界信息.实验结果表明:用基于三坐标测量机的单摄像机共轴立体视觉测量方法获取的曲面边界平均误差为0.268 mm,基本满足逆向工程中对引导性曲面边界的测量精度要求.     

基于双目序列图像的测距定位与自车速度估计

为了确定车辆在行驶过程中的相对位置与速度,提出一种基于双目序列图像的实时测距定位及自车速度估计方法。该方法利用车载双目视觉传感器采集周围环境的序列图像,并对同一时刻的左右图像进行基于SURF(speeded up robust features)特征的立体匹配,以获取环境特征点的景深,实现车辆测距定位;同时又对相邻两帧图像进行基于SURF特征的跟踪匹配,并通过对应匹配点在相邻两帧摄像机坐标系下的三维坐标,计算出摄像机坐标系在车辆运动前后的变换参数,根据变换参数估算出车辆的行驶速度。模拟实验表明,该方法具有良好的可行性,速度计算结果比较稳定,平均误差均在6%以内。     

一种单双目视觉系统结合的三维测量方法

在投影栅相位法的单日和双目三维测量结构的基础上,提出了一种单双目结合的三维测量方法.采用双目测量系统的架构,对两相机的公共区域使用双目的方法进行复现,同时分别将两个相机与投影仪组成两个单目测量系统,通过标定的统一可以将两者的世界坐标系统一到一个共同的基准上,利用单目的测量结果对双目测量的哪缺失区域进行填补.在对石膏头像的测量中,利用该方法避免了双目测量中在鼻梁附近出现的数据丢失.在保证双目复现区域精度的基础上,该方法有效地改进了测量结果的完整性.     

结合Levenberg-Marquardt算法的垂直视差消减方法

垂直视差的存在是影响立体视频观视舒适度的主要因素。为了在不影响水平视差的条件下实现对垂直视差的消减,本文引入Levenberg-Marquardt(L-M)非线性算法实现变换矩阵的精确求解。首先用抗缩放、旋转及仿射变换的SIFT(Scale-invariant feature transform)特征匹配算法检测出双目图像对的特征匹配点,然后根据匹配点的坐标位置运用L-M算法计算可消减垂直视差的变换矩阵,将变换矩阵作用于目标图像,计算出该视图每个像素点的新坐标位置。实验结果表明:与利用线性算法求解二维射影变换矩阵的垂直视差消减方法相比,本文提出的求解方法在垂直视差消减上比该算法提高了约0.029 1~0.323 2个像素,对水平视差的影响比该算法降低了约0.118 7~1.139 1个像素。因此本文提出的方法对垂直视差的消减起到了优化作用。     

基于视觉测量的飞行器舵面角位移传感器标定

提出一种基于计算机单目视觉的飞行器副翼、襟翼、方向舵和升降舵角位移传感器的非接触标定方法.用共面的两个特征圆组成一标定靶固定在飞行器舵面上,用一台定焦数码摄像机对标定靶拍照,获得特征圆数字图像.经图像分析确定特征圆圆心及直径在像面上的透视投影位置和长度,根据透视投影逆变换原理建立物和像空间坐标关系的解算模型,进而导出靶面平面方程.飞行器舵面角位移则由标定靶面的法线方向余弦来表示.仿真结果表明,该方法具有标定过程快速、简单和准确的特点.不需事先标定摄像机内外部参量,其标定准确度优于0.2°.     

基于特征点及优化理论的图像自动拼接方法

提出了一种新的图像拼接方法,首先利用相位一致性(phase congruency)算法进行特征点检测,利用本文提出的匹配点优选策略进行特征点对自动选取,然后用LM(Levenberg-Marquardt)算法进一步优化变换矩阵,最后对拼接结果进行融合处理,获得无缝拼接的图像.该方法把基于特征点和基于优化理论的拼接方法有效相结合,且能充分利用图像重叠部分的信息,在一定程度上克服了噪声及光照不均的影响,较传统方法具有更强的鲁棒性和更高的拼接精确度.试验结果证明了该方法的有效性.