Research and realization of an auto-calibration technique based on stereovision

The purpose of this research is to analyse the present-day state of calibration techniques and to realize an auto-calibration technique based on a projected grating 3D measuring system. An auto-calibration technique, called multiple target tracking for detecting outlines based on random placing and regular numbers, was proposed. The practical algorithm was also presented at the same time. According to this arithmetic, the relevant experimental result was gained. Furthermore, the precision of the calculation result was analyzed. The results showed that the operation was simplified, the orientation precision of image outline edges was ensured and calibration precision was kept within 0.02–0.05 mm by using the arithmetic in this work. The research verified the feasibility of auto-calibration, providing arithmetic that is extremely useful for the industrial application of computer vision technologies. The paper deals with experimental work on innovative techniques for which the data have not been seen in the literature. In particular, an original auto-calibration technique, which is named as multiple target tracking for detecting outlines based on random placing and regular numbers, was provided.     

基于多判据的多目视觉手势立体姿态检测系统研究

为了精确识别人手姿态用于机器手控制,文中讨论一种基于计算机视觉的手势立体姿态检测的新方法.该方法利用多目视觉之间的配合,有效地解决了检测识别时手部关键节点互相遮档的关键问题.采用了自适应阈值分割、harris角点检测、外极线约束等几种合理、有效的点的匹配算法,对不同摄像机拍摄到的手部关键节点进行排序,这样不仅解决了特征...     

一种新的双目固定式机器人三维视觉定位方法

三维视觉定位是基于位置的机器人视觉伺服的重要步骤,直接影响到系统的控制精度。本文针对眼固定式双目视觉机器人,提出了一种基于基坐标系的直接视觉定位方法,通过点-极线对建立齐次线性方程组以求解包含了双摄像机相对位置等信息的基本矩阵,再根据基本矩阵的性质将其分解为双摄像机相对于机器人基坐标系的投影矩阵,进而通过由空间平面确定的直线方程直接进行基于基坐标系的重建。该方法简单直接易于实现,相关实验通过将重建得到的坐标与实际坐标相比较,验证了该定位方法的精确性和有效性。     

fMRI analysis of excessive binocular disparity on the human brain

The aim of this study is to evaluate brain regions related with excessive binocular disparity that may be linked to stereoscopic visual fatigue. In stereoscopic displays, excessive binocular disparity may generate blurring or double vision in the stereovision and induce unnatural oscillations in accommodation and vergence. These phenomena may lead to visual fatigue and activation (or deactivation) of human brain related with sensory and eye movement functions. A functional magnetic resonance imaging (fMRI) method is used to investigate the effect of excessive binocular disparity on human brain. Subjective assessments of visual fatigue are also conducted with the same stimuli as the fMRI experiment. Based on the subjective assessment results, participants are classified into low‐ and high‐fatigue groups. From the fMRI experiments, the high‐fatigue group showed more activation at the intraparietal sulcus (IPS) than the low‐fatigue group, when viewing an excessive disparity stimulus. The results showed that the excessive binocular disparity stimulus may induce overload to the IPS region, which is related with stereo processing and saccadic eye movement. In addition, it could be possible to use fMRI as an objective measurement method for understanding the stereoscopic visual fatigue when stimuli with excessive binocular disparity are applied.     

双目摄像机标定与特征点匹配方法的研究

传统标定方法具有实验环境要求高、结果精确度低、鲁棒性差等显著缺点,为此提出一种基于软件编程的主动视觉标定方法。通过建立摄像机针孔成像线性模型,考虑畸变影响的非线性模型矫正,推导出双目摄像机标定参数,并应用软件编程实现摄相机标定,获得精度高、鲁棒性较好的结果。同时,针对当前已有的图像匹配算法,对图像尺度变化适应性较差等问题,以Harris算子为基础,通过增加图像变换尺度参数,得到具有尺度不变性的改进算法。基于软件编程实现特征点坐标提取与匹配,结果显示改进后算法耗时变短、计算结果精度和鲁棒性均有所提高,为深入研究双目摄像机障碍物识别与路径规划奠定了基础。     

光学坐标测量系统技术研究

光学坐标测量系统是建立在数字近景测量技术基础上的一种新型精密测量系统.它具有便携性好、精度高、测量范围大、受环境干扰小等优点,适合工业工程的现场测量.针对工业现场精密测量的需求,分析了立体视觉原理以及通用坐标测量的数学模型.目前系统的精度接近±0.1 mm/m,整个系统已初步成型,能够对实物工件进行测量,其测量精度、自动化程度令人满意.     

Guiding the welding robot to the initial welding position with visual method

Using step pattern match technology with variational resolution can recognize the position and orientation of the weld seam in the image. According to using the image segmentation method based on pattern match, not only advanced the speed and anti-jamming capability, but also captured the edge information of the weld seam and the edge of the workpiece, and the image coordinate of the initial welding position can be obtained. The matrix for hand-eye relationship of the robot can be calculated by adopting the rapid calculation method. According to the depth calculating principle with the special point matching using binocular stereovision, the initial welding position can be confirmed by calculating the middle point of the perpendicular line of two radials in the space, and the function to guide the welding robot to the initial welding position can be realized.     

基于SLM显微立体视觉模型的3D微定位研究

基于体视显微镜(Stereolightmicroscope,SLM)的显微立体视觉已经在微操作领域应用。本文研究了基于SLM显微立体视觉模型的微操作系统中的三维微观定位问题。通过对SLM双光路的分析,给出了描述二维图像空间和三维物空间映射的弱非线性显微立体视觉模型。采用立体匹配算法和目标识别两种方式对运动图像序列中的目标对象进行捕捉,可以批量给出立体图像中相关点的坐标。利用显微立体视觉理论模型和显微图像处理实现了微操作系统中的微观3D定位。     

基于ARToolkit立体视觉成像增强现实系统的研究

沉浸性是虚拟现实系统最为吸引人的特点，也是研究的重点和热点。而增强现实技术是将计算机生成的虚拟环境的图像和真实环境的景象叠加显示到用户所佩带的辅助显示设备来获得真实的沉浸感。ARToolkit为增强现实技术的应用提供了一种方便快捷的开发工具．本文介绍了一个使用ARToolkit实现具有立体视觉成像的人机交互系统。     

一种机器人立体视觉匹配方法的研究

针对区域匹配计算量大而特征匹配算法复杂的缺点,采用了一种以边缘点为匹配基元,使用双阈值判断的灰度相关分阶段立体匹配方法。