Research on the application of single camera stereo vision sensor in three-dimensional point measurement

A single camera stereo vision sensor model based on planar mirror imaging is proposed for measuring a three-dimensional point. The model consists of a CCD camera and a planar mirror. Using planar mirror reflections of a scene, a picture with parallax is obtained by shooting the target object and its virtual image. This is equivalent to shooting the target object from different angles with the camera and the virtual camera in the planar mirror, so it has the function of binocular stereo vision. In addition, the measurement theory of the three-dimensional point is discussed. The mathematical model of a single camera stereo vision sensor is established, the intrinsic and extrinsic parameters are calibrated, and the corresponding experiment has been done. The experimental results show that the measuring method is convenient and effective; it also has the advantages of simple structure, convenient adjustment, and is especially suitable for short-distance measurement with high precision.     

立体视觉测量系统的空间分辨力和结构参数设置

立体视觉测量系统的空间分辨力随着物体的空间位置和移动方向的变化而变化,系统的空间分辨力高低在很大程度上会影响整个系统的测量精度。本文根据立体视觉测量系统的成像公式,对整个系统观察范围内的所有空间点的空间分辨力进行了详细分析与计算。结果表明,两个 CCD夹角在 80°~100°时系统的空间分辨力最高,并且 X方向的空间分辨力整体上高于 Y方向, Z方向的空间分辨力变化相对较小,最终的实验结果和仿真结果相吻合,根据系统空间分辨力的分布规律,本文制定出了制出了空间分辨力最优的立体视觉系统的参数设置方案。     

Improved depth map through optimal axis stereo

Feature-based stereo correspondence techniques suffer from the major limitation that it is difficult to match along epipolar lines and this often results in a sparse set of depth points. Past researchers attempted to solve this problem through trinocular stereo. In this paper, a new method has been proposed for reducing the sparsity of depth points by orienting the epipolar line of the cameras in a direction that maximizes the number of feature points. The corresponding epipolar axis has been termed as the optimal axis. Our analytical as well as simulation results have established that for a limited edge scenario, the proposed approach can lead to considerable improvement in the number of feature points that can be matched. We have introduced a figure-of-merit for the optimal axis and discussed how it is qualitatively related to the variance of the probability density function (pdf). We have also presented the results of our simulation experiment, termed as the random stick experiment. Finally, we have also shown the results of improved reconstructed surface of a synthetic image using optimal axis alignment.     

基于多视图立体视觉的沙堆三维尺寸测量研究

利用从运动中恢复结构方法(SFM),提出了一种基于多视图立体视觉的沙堆三维重建及三维尺寸测量方法。首先根据SFM方法的求解不稳定特点,结合光束平差法对SFM求解过程进行分析及优化;其次针对SFM重建结果为稀疏点云的问题,利用基于面片的稠密重建算法重新生成稠密的三维点云,再利用泊松算法对密集点云进行三维曲面重建;最后获得模型的三维尺寸信息。对某建筑工地的沙堆进行了三维尺寸的测量实验,实验结果验证了该方法的有效及可行性,提高了重建能力及精度,同时考虑了目标实际测量误差与重建误差,能够满足实际智能测量的应用需求。     

基于双目立体视觉的物流包装箱尺寸测量研究

目的针对物流行业运输中包装箱的非接触自动测量,提出一种基于改进SURF配准算法的双目立体尺寸测量方法。方法首先采用二进制FREAK描述子代替传统SURF的描述子,解决传统SURF描述子计算耗时、描述向量生成依赖于特征主方向,且主方向计算误差会在后续步骤中出现传导放大的缺点;其次,采用PROSAC删除误匹配点,并利用FREAK级联匹配的方式进一步提高算法的匹配速度和匹配准确率。最后,利用视差优化和边缘提取算法获得精确三维空间体,实现非接触尺寸测量。结果实验表明改进算法可快速提取图片特征点并准确匹配,对不同规格包装箱检测结果显示,基于改进算法的测量方法测量误差小,检测速度快。结论改进图像匹配算法可有效提高图像匹配准确率,减少测量时间,对于提高物流行业运输效率、减少人工成本具有重要意义。     

双摄像机光笔式三维坐标测量系统研究

基于双目立体视觉传感器三维测量模型和空间坐标变换原理,采用最小二乘冗余算法,讨论了双摄像机测量空间三维点坐标的基本原理,建立了视觉测量系统的非线性测量方程.通过实验验证了双摄像机光笔式三维坐标视觉测量系统建立的可行性.     

双目视觉中距离约束的小波变换同名点匹配

针对一类特殊小波变换系数不同尺度下的过零点能提供在不同尺度下信号急速变化点的位置信息,提出了一种基于小波变换的多尺度过零点的双目立体视觉模型的同名点匹配方法,该方法采用由粗到细的匹配策略,利用转化的距离信息先匹配大尺度的小波变换系数的过零点,记录其过零点位置信息,然后应用顺序约束,即物体在左右影像点的投影顺序的一致性,匹配小尺度的小波变换系数的过零点,降低了同名点匹配搜索的复杂性,减少了误匹配,解决了同名点准确匹配难、计算量大等问题.采用该方法对篦冷机内水泥熟料高度进行测量,实验表明该方法能较精确的得出水泥熟料料层的分布状况.     

一种基于立体靶标定位的三维重建方法

针对线激光传感器在特征信息匮乏引起的数据拼接误差较大的问题,提出了一种基于立体靶标定位的线激光数据拼接方法。通过双目立体视觉的空间几何约束构建靶标点库,实现立体靶标坐标系与线激光坐标系的位置标定;通过Canny边缘检测、亚像素边缘提取、椭圆拟合等算法对圆形特征点进行识别定位;将采集的局部标志点与靶标点库进行同源点匹配,解算线激光传感器的实时位姿;采用坐标系转换将线激光初始坐标与全局坐标系进行统一,实现点云的三维重建。实验结果表明:靶标标定的平均绝对误差为0.078mm,测量的标准件拟合平均偏差为0.127mm,与三坐标测量机)CMM)对比,该方法的测量平均偏差为0.165mm,与机器人定位拼接和深度相机测量结果对比,搭建的测量系统的平均测量误差和标准偏差较小,可以满足对复杂曲面的多角度实时扫描需求。     

基于视差空间运动估计的高精度立体视觉定位

立体视觉定位算法的运动估计通常在3D欧式空间中进行,但由于特征点3D坐标的噪声各向异性且分布不均匀,3D重建在深度方向上比另两个方向上的准确性差,从而导致3D欧式空间运动估计精确不高.本文提出了一种新的基于视差空间运动估计的高精度立体视觉定位算法.算法首先采用视差空间4点闭环线性解法和RANSAC算法得到初始鲁棒运动估计和匹配内点.接着,利用新的视差空间再投影误差函数提出了基于LM算法的视差空间运动参数非线性优化方法,对初始运动参数进一步优化.视差空间噪声分布均匀且各向同性,本文的初始运动参数线性估计和非线性优化都在视差空间中进行且能达到全局最小.仿真实验和真实实验结果表明,本文算法能得到高精度的立体视觉定位结果,优于传统的3D欧式空间运动估计方法.     

立体电视技术的发展趋势

立体电视可以使电视画面再现立体视觉的真实效果，不仅可以用于现代的信息交流和文化活动，而且也可用于科学技术研究，工业设计、建设和生产以及医学和军事事业等等，显著提高其工作效率，因此已成为新的电视技术的发展方向和研究重点。本文阐述了近几年来国内外在这一方面的研究进展，包括常说的立体电视STV及全息电视HTV，和立本视觉及立体电视的基本原理。     

基于离焦二值显示和条纹投影的复合表面三维测量方法

由于复合表面物体中漫反射部分和镜面部分反射性质不同,受到相机景深的限制,镜面成像的正弦条纹发生离焦,从而引起相位误差。为了实现复合表面物体的高效、高精度测量,本文提出了一种离焦二值结合正弦条纹的复合表面三维形貌测量方法。首先,本文基于刃边法与二次模糊法对系统离焦程度进行分区标定,解决了由于相机倾斜放置导致参考面离焦程度不同的问题。然后,建立二值条纹相位误差模型,确定最佳条纹宽度和离焦量范围。最后,对轻微离焦区域的二值条纹进行离焦补偿,确保相机采集的条纹均在最佳离焦范围内。在此基础上进行三维形貌测量。实验结果表明,所提方法使镜面部分误差从原来的0.033 mm降至0.019 mm,提高了复合表面测量精度。

     

Pose estimation for autonomous grasping with a robotic arm system

A robust and accurate method for estimating the 3-D pose of a planar rigid object is presented. This article demonstrates that 3-D pose estimation becomes feasible by using the 2-D tracking points on an object of scale-invariant feature transform (SIFT) and 3-D point cloud detected by stereo vision on an object, assuming that a 3-D geometric model of an object is known a priori. The roll and pitch angles of an object are estimated by the normal vector of approximate plane of 3-D point cloud on an object and the yaw angle is estimated by 2-D tracking point on an object of SIFT. Accurate object detection and localization in the camera coordinate system is crucial for grasping. In the motion planning, the bidirectional rapidly exploring random tree algorithm is used to search for a valid path for efficient grasping. Our robot arm can robustly and autonomously grasp a randomly rotative rigid object detected by SIFT in 3-D space. We have realized a grasping scenario with a dexterous arm (ADAM) such that an object in front of ADAM can be grasped. This demonstration shows how the proposed components build a dexterous and robust system integrating object detection, pose estimation, and motion planning.     

Application of a Multi‐Camera Stereo DIC Set‐up to Assess Strain Fields in an Erichsen Test: Methodology and Validation

Abstract: A multi‐camera stereo digital image correlation (MC‐DIC) set‐up is presented to obtain full displacement and strain fields of a sheet‐metal specimen subjected to an Erichsen test. The set‐up is composed of several conventional stereo DIC systems (two camera set‐up), each of which tracks the deformation of an aspect of the specimen. The individual measurements, including the geometries and the displacements, are then converted to the same reference frame to integrate into a global view. Afterwards, the strain is calculated based on the composed displacement field. It is found that the geometry and the displacement fields of the bulged specimen are ideally stitched, and smooth strain fields are obtained. The influences of the reference frame transformation and the stitching procedure on the MC‐DIC measurement are investigated. A rigid motion test is performed to validate the displacement measurement. It is discussed that the global field is more reliable than the individual measurements for this test set‐up.     

精密微小装配中的传感器与测量技术

装配是高性能精密微小器件或产品制造过程中的关键环节,由于零件及其关键结构的尺寸微小,微小装配必然是基于传感器与测量技术的精密装配。在微小零件装配过程中,需要精确测量待装配零件之间的相对位置和姿态的偏差,控制配合零件之间的接触力或接触状态。首先对用于精密微小装配的传感器技术进行了概述;然后结合精密微小装配中的应用需求,对机器视觉、力觉等主要传感器与测量技术进行了综述,并分析了精密测量与装配控制的技术与方法,旨在对精密装配相关的技术开发、装配设备研制提供参考和借鉴。     

立体视觉曲面重建与系统误差分析

采用立体视觉空间曲面重建技术对三维曲面表面成像进行边缘提取、图像匹配、匹配点空间位置计算等步骤,得到三维曲面表面点的空间位置,利用空间点信息对三维曲面形状进行重建,恢复曲面三维形状;并讨论了立体视觉系统的摄像机分辨率、测量范围和摄像机间距等参数之间的关系.利用该方法对堆积物表面形状及体积进行测量实验结果表明,该方法能准确、快速、方便地给出三维曲面的形状.     

Depth recovery and refinement from a single image using defocus cues

We present a technique to recover and refine the depth map from a single image captured by a conventional camera in this paper. Our method builds on the universal imaging principle: only scene at the focus distance will converge to a single sharp point on imaging sensor but other scene will yield different blur effects varying with its distance from the camera lens. We first estimate depth values at edge locations via spectrum contrast and then recover the full depth map using a depth matting optimization method. Due to the fact that some blur textures such as soft shadows or blur patterns will produce ambiguity results during the procedure of depth estimation, we use a total variation-based image smoothing method to smooth the original image, a smoothed image with detailed texture being suppressed can be generated. Taking this smoothed image as reference image, a guided filter is used to refine the final depth map.     

一种基于ORB特征的水下立体匹配方法

针对水下环境中传统算法对双目图像匹配时存在速度慢、误匹配较多等问题,提出一种基于ORB(的特征检测和曲线极线约束相结合的水下立体匹配方法。先检测图像的特征点,生成描述子,并进行特征匹配;然后根据折射定律,结合双目相机的内外参数,推导出水下曲线极线;最后结合水下曲线极线约束,剔除误匹配点。实验结果表明,相比传统的SIFT算法与曲线约束,论文提出的立体匹配方法在有效控制误匹配的情况下,显著提高了运算速度,对提升水下双目视觉系统的快速处理能力具有实践意义。     

光切法三维轮廓测量中的离焦误差研究

本文分析了光切法三维轮廓测量中离焦误差的产生原因及其对的影响，探讨了无离焦倾斜接收方式消除此项误差的原理及其缺陷，在此基础上提出了既能消除误差又能解决倾斜收方式缺点的有焦正接收方式的消视差校一，较满意地解决了离焦误差问题。     

一种基于频谱分析的离焦深度自动对焦法

通过计算2幅不同离焦位置的图像频谱的径向分布,推算出目标物体的离焦深度,从而调 整镜头位置完成自动对焦。算法适用于任意目标物体,尽管是基于频谱的,但是并不需要计算离焦图像的频谱,算法精度可达4%,鲁棒性良好。