Estimation of measurement uncertainty in stereo vision system

Stereo vision systems are becoming increasingly popular and widespread. These systems are widely used in many applications, such as navigation of autonomous mobile robots, 3D measurements, object tracking, the movie industry, augmented reality or people tracking and identification systems. Surprisingly, in the literature, little attention is paid to practical verification procedures in which proper operation of the calibrated stereo vision system can be demonstrated. Therefore, in this paper, a novel approach is proposed that allows accurate estimation of the measurement uncertainty of the (x,y,z) coordinates reconstructed by the stereo vision system. The proposed method does not require any additional equipment beyond the standard calibration board and a general-purpose laser distance meter. The authors introduce a simulation model and mathematical formulas that can be employed to determine the accuracy of the stereo vision system precisely along each of the X, Y and Z axes. The measurement uncertainties obtained are statistically reliable because they are calculated with the use of a large amount of data. A series of experiments are conducted to confirm the correctness of the presented approach and to demonstrate how to apply the developed solution in practical applications. The proposed method can be easily integrated with both newly created and existing solutions because it does not require the introduction of any modifications in the system structure and calibration process.     

Freight train gauge-exceeding detection based on three-dimensional stereo vision measurement

We present a method for freight train gauge-exceeding detection based on three-dimensional (3D) stereo vision measurement. To reach high measurement accuracy under large-scale situation, the factors which influence the 3D measurement error are analyzed in detail. Algorithm to accurately extract the laser stripe feature projected by the measurement system is described. With the obtained stripe features, the 3D structure of the freight train can be reconstructed with nonlinear optimization procedure. Specially designed targets are used to identify the global coordinate system for gauge-exceeding detection. A prototype has been developed and the reliability and accuracy have been demonstrated by external field experiment.     

Using models to improve stereo reconstruction

The authors propose the combination of photometric and stereometric information to solve the stereo vision problem in the case of a man-made environment. A method to introduce geometrical models in the stereo process in order to improve the accuracy of the depth measurement and to extend the depth map to points where no measurements have been made is presented. This method is based on a parameterization of the object surfaces and relies on a systematic comparison of the result of a stereo process with the photometric (or gray-level) image. The proposed approach improves the accuracy of the stereo information and its density by introducing a hypothesis on the object surfaces. Two kinds of hypothesis are developed: planar and quadratic objects. Reconstructions of complex scenes are given     

双目视觉测量传感器研究

研究了按照激光三角测量原理由 1个线激光器及 2个CCD摄像机组成的双目视觉测量传感器。探讨了 2个CCD摄像机的摆放位置及其对测量精度的影响,确定了其几何参数。在此基础上,论述了其工作过程,包括其标定方法、标定过程、扫描图像采集、特征提取、特征匹配及三维数据生成。该双目视觉测量传感器配合扫描机构(如三坐标测量机 )即可对物体进行非接触式三维激光扫描测量,其测量速度快,精度比较高,可以应用于逆向工程领域。     

基于单相机的全向深度图获取

为了搜寻移动机器人周围最大的可通行区域,采用全向立体视觉系统,提出获取可靠的致密三维深度图方法。视觉系统由1个普通相机和2个双曲面镜组成。当系统标定后,空间点的三维坐标可以通过匹配上下镜面的成像点计算得出。匹配方法分3步：最大FX匹配,特征匹配和歧义去除。定义合适的能量函数通过动态规划来实现剩余点的匹配。实验表明该系统精度高、具有实用价值。     

基于栅格模型的双目移动机器人三维场景重建

以投影几何学以及双目立体视觉原理为理论基础,对移动机器人的三维重建技术进行研究,对移动机器人漫道过程中所在的兴趣区域的场景进行较为精确的建模.设计了机器人的快速建模方法,利用迭代最近点算法(ICP),完成了多个局部三维场景模型的融合.同时,结合栅格投射理论,完成了对全局三维场景模型的更新.利用栅格模型重建的三维场景,具有环境信息丰富,模型描述精确的特点,可以应用于移动机器人导航领域.     

栅格法视觉传感集成及机器人实时避障

研究移动机器人在室内环境下集成双目视觉和激光测距仪信息进行障碍物实时检测。由双目视觉系统检测环境获取视差信息,通过直接对视差信息进行地平面拟合的方法快速检测障碍物;拟合过程中采用了随机采样一致性估计算法去除干扰点的影响,提高了障碍物检测的鲁棒性。用栅格地图表示基于机器人坐标系的地平面障碍物信息并对栅格信息进行提取,最后把双目视觉与激光测距得到的栅格信息进行集成。实验表明,通过传感信息集成,移动机器人既得到了充分的障碍物信息,又保证了检测的实时性、准确性。     

A high-sensitivity 3D shape measurement method using a microscope

Optical microscopes generally have magnifications ranging from several tens to several thousands and they are often used to observe micro-specimens. Three-dimensional (3D) shape measurements of specimen surfaces are used in a wide range of fields including medicine, pharmacy, life science, and materials science. Conventional methods invariably employ 3D measurement techniques that involve adjusting the focal length of a microscope, which requires a complex automatic adjustment mechanism. Furthermore, since the depth is determined by controlling the focal length, 3D measurements have a low sensitivity. To realize a 3D measurement system with a simple configuration and a high measurement accuracy, we propose a high-sensitivity 3D shape measurement method that employs a microscope and is based on a pattern projection technique. The measurement system consists simply of a conventional optical microscope, a line laser, and a computer. The 3D measurement method employs slit pattern projection. A slit pattern produced by the line laser beam is projected onto the target surface and a reflected image is obtained using a camera installed on the microscope. 3D shape information of the target is obtained using image processing based on the triangulation method. We obtain 3D shape information of the target surface by scanning the slit projection pattern across most of the target surfaces by translating the stage on which the specimen is mounted. The experimental results demonstrate the effectiveness of the proposed method.     

基于立体视觉的水下三维测量系统研究

随着我国海洋战略的提出,对于海洋观测技术和装备的需求日趋迫切。针对现有水下成像系统无法实现精确三维测量这一难题,该文提出了一种基于双目立体视觉原理的水下三维测量系统研究方法,并对其可行性进行了验证。针对水下成像过程存在的水体界面折射问题,该文提出了相应的相机成像模型及系统参数标定方法,建立了防水深度达 30 m 的双目水下测量及照明装置,并在水池、近海条件下进行了实地测试。实验结果显示,在水体条件较好的情况下,系统观测距离可达 8 m 以上,有效测量距离为 0.5～4.5 m,在 0.5 m 和 4.5 m 距离处的测量误差分别为 2 mm 和 20 mm。实验验证了 水下双目成像模型、立体标定、测量模型等方法的有效性和精确性,可为水下检修作业等海洋工程行业提供一种有效的三维测量技术手段。     

基于双目内窥镜的散斑三维重建系统研究

传统的内窥镜只能提供清晰的图像,无法进行三维测量和三维重建.该文提出一种基于立体视觉原理的双目内窥镜系统,用于实现三维测量和三维重建,并开发了一套基于双目内窥镜的散斑三维重建系统.为了提高系统的标定精度和三维重建质量,该文提出一种高精度双目内窥镜标定参数优化方法及基于光轴双次旋转的立体校正算法.其中,测量系统由一个结构...     

结构光与双目视觉相结合的三维测量

在三维测量技术中,传统的双目立体视觉方法计算量大,对没有明显特征的图像,匹配精度较低。本文将基于结构光的三维测量技术与双目成像技术相结合,解决了特征点搜索的困难,提高了测量的精度。与传统结构光成像技术相比,采用常规的双相机立体标定,不需要进行投影仪标定,降低了系统的复杂性,提升了系统的可操作性和灵活性。最后,运用该技术进行三维测量实验,测量结果表明了该技术的可行性。     

Stereo vision system for precision dimensional inspection of 3D holes

This paper presents a machine vision system for the high-accuracy 3D measurement of holes on the surface of industrial components. This is a very important application for inline quality inspection in assembly plants. A CAD-based stereo vision approach is adopted. The introduction of several novel techniques enables the system to achieve high robustness in versatile industrial environments, rapid response, and accuracy below 0.1 mm. These are demonstrated by extensive experiments with synthetic and real data.Received: 10 May 2002, Accepted: 25 April 2003, Published online: 7 October 2003     

一种基于SIFT特征的机器人环境感知双目立体视觉系统

针对双目立体视觉系统在机器人环境感知领域中存在的立体匹配以及测量精度问题,设计一种基于SIFT特征的双目立体视觉测量系统.利用SIFT特征良好的旋转、尺度、光照不变性等特性,有效地解决双目立体视觉系统的匹配问题,同时将SIFT算法在由FPGA和DSP组成的嵌入式系统上实现,显著地提高测量系统的实时性.提出一种基于二次多项式的误差补偿方法,对系统的测量结果进行补偿,弥补双目立体视觉系统测量误差随测量距离增加而增加的不足,从而提高系统测量精度.通过实际的测量实验、移动机器人环境感知实验以及与现有双目立体视觉产品的对比实验结果表明,系统能够很好地解决双目立体视觉的立体匹配和精度问题,并且能较好地应用于移动机器人环境感知任务中.     

基于旋转视觉的三维姿态重构方法及精度分析

考虑电子元件的多样化、精细化及PCB集合度越来越高,这对元件组装设备的精度要求不断提升;针对自动插件机视觉系统要求精度、实时性高,系统结构空间狭小等特点,基于旋转立体视觉建立了针脚末端三维坐标视觉系统的数学模型,并在旋转视觉的代数重构法基础上提出等价双目视觉的三角重构法;通过理论分析和仿真,推导并验证了旋转视觉的关键部件与关键参数的精度对针脚位姿测量精度影响的定量分析方法;借助于等价双目视觉的三角分析法,找到了在某些位置下针脚位姿测量精度发生异常的原因和规律;提出的重构方法及精度分析方法可为高精度旋转视觉的设计选型、优化和高效使用提供指导.     

基于格雷码和多步相移法的双目立体视觉三维测量技术研究

传统的被动式双目立体视觉三维测量技术,具有操作简单,使用灵活方便,相机标定技术成熟的优点,但是对于特征点稀疏图像,寻找匹配点困难,匹配精度低。编码结构光测量方式通过向待测物体投射特定的编码图案,获取编码图像进行解码求解物体的三维信息,具有着测量精度高,速度快的优点,但是存在着投影仪标定精度低,实现难度大的缺点。提出了将双目立体视觉和编码结构光相结合的三维测量方法,在完成双目校正的基础上,向待测物体投射格雷码图案和多步相移图案,给予被测物体容易识别和可控制的特征信息,最后求取物体的三维信息。而且通过实验论证了投射多步相移图案比起4步相移图案,测量精度更高,能够更好的体现物体细节。     

Three-dimensional point cloud alignment detecting fiducial markers by structured light stereo imaging

In recent years, various methodologies of shape reconstruction have been proposed with the aim at creating Computer-Aided Design models by digitising physical objects using optical sensors. Generally, the acquisition of 3D geometrical data includes crucial tasks, such as planning scanning strategies and aligning different point clouds by multiple view approaches, which differ for user’s interaction and hardware cost. This paper describes a methodology to automatically measure three-dimensional coordinates of fiducial markers to be used as references to align point clouds obtained by an active stereo vision system based on structured light projection. Intensity-based algorithms and stereo vision principles are combined to detect passive fiducial markers localised in a scene. 3D markers are uniquely recognised on the basis of geometrical similarities. The correlation between fiducial markers and point clouds allows the digital creation of complete object surfaces. The technology has been validated by experimental tests based on nominal benchmarks and reconstructions of target objects with complex shapes.     

一种无标记点三维点云自动拼接技术

基于相位投影和双目的三维光学测量系统已经广泛应用于各领域.受投影光测量系统单次测量范围大小的限制,对大型物体的测量需要在表面粘贴圆形标记点进行多次拼接的缺点,探讨一种基于SIFT的无标记点自动拼接技术.该技术采用SIFT方法获取两次测量的特征点,其次结合RANSAC求出图像特征点的匹配关系,再根据立体匹配中图像特征点与三维点云之间的对应关系,将二维特征点的对应关系映射到三维点云的对应关系上,最后由SVD奇异值分解算法求得旋转和平移矩阵实现拼接.实验证明:该方法可以避免在被测量对象上粘贴标记点,能够快速准确地实现自动拼接.     

目标位姿测量中的三维视觉方法

要测量出一组特征点分别在两个空间坐标系下的坐标，就可以求解两个空间目标间的位姿关系，实现上述目标位姿测量方法的前提条件是要保证该组特征点在不同坐标系下，其位置关系相同，但计算误差的存在却破坏了这种固定的位置关系，为此，提出了两种基于模型的三维视觉方法－基于模型的单目视觉和基于模型的双目视觉，前者从视觉计算的物理意义入手，通过简单的约束迭代求解实现模型约束，后者则将简单的约束最小二乘法和基于模型的单目视觉方法融合在一起来实现模型约束，引入模型约束后，单目视觉方法可以达到很高的测量精度，而基于模型的双目视觉较传统的无模型立体视觉方法位移精度提高有限，但姿态精度提高很多。     

Human-Assisted Virtual Environment Modeling for Robots

In order to avoid the complex calculation and poor robustness in automatic visual modeling process, a man-machine interaction based stereo vision system is developed for modeling an unknown environment. The operator's knowledge about a scene is used as a guidance for modeling 3D environment. The modeling technique has advantage in terms of reliability and robustness over other automatic modeling approaches. The data points needed for modeling an objects are obtained through the intersection of lines, or calculation from equations of curve, derived via fitting from human guided edge detection. The modeling accuracy is ensured by using image feature extraction. A multi-viewpoint modeling approach has been developed in order to deal with occlusion problems.Both accuracy and speed issues are addressed in this paper. The system implementation and some 3D measurements on real scene have been performed using cameras lenses of 16 mm and 8 mm with an accuracy 0.5 mm and 0.8 mm over the field of view, respectively. The virtual environment rendering based on the modeling data of real scenes with known model of mobile robot is given at the end of this paper.     

一种改进的三维人脸重构方法

提出一种改进的三维人脸重构方法。该方法采用基于单个相机的双目立体视觉系统对人脸进行采样,根据人脸对称性假设,运用补洞与纠错技术进行自动点云优化。继而采用简化的Candide-3模型作为细分初始控制网格,局部加细地进行细分曲面分层次拟合操作,采用测地线映射技术对不同表情进行归一化,并分别建立人脸数据库。实验结果表明,采用单相机立体视觉系统在提高重建精度的同时,很大程度上避免由于双相机拍摄不同步引起的重建鲁棒性降低问题。而采用细分曲面作为存储结构,在节约空间的前提下,为分层次比对筛选提供理论支持。该系统成本较低,适合在许多领域推广应用。