A machine vision approach to seam tracking in real-time in PAW of large-diameter stainless steel tube

Manual monitoring and seam tracking through watching weld pool images in real-time, by naked eyes or by industrial TV, are experience-depended, subjective, labor intensive, and sometimes biased. So it is necessary to realize the automation of computer-aided seam tracking. A PAW (plasma arc welding) seam tracking system was developed, which senses the molten pool and the seam in one frame by a vision sensor, and then detects the seam deviation to adjust the work piece motion adaptively to the seam position sensed by vision sensor. A novel molten pool area image-processing algorithm based on machine vision was proposed. The algorithm processes each image at the speed of 20 frames/second in real-time to extract three feature variables to get the seam deviation. It is proved experimentally that the algorithm is very fast and effective. Issues related to the algorithm are also discussed.     

Host odor and visual stimulus interaction during intratree host finding behavior ofRhagoletis pomonella flies

Responses ofRhagoletis pomonella (Walsh) (Diptera: Tephritidae) flies to host fruit visual stimuli (apples or models of apples) and chemical stimuli (synthetic apple volatile blend) were studied in semidwarf field-caged apple trees. Three different fruit or model densities (1, 4, or 16 fruit or models/ tree) and two odor release rates [ca. 0.7g/hr (close to the natural release rate of a ripe apple) and ca. 500g/hr (amount of odor released by commercially sold apple maggot traps)] were tested. Individually released flies were followed as they moved within a tree for a maximum of 20 min. We recorded three-dimensional search paths followed by foraging flies and computed such variables as total relative distance traveled before alighting on a fruit or model, track length between individual alightment sites, and directness of flight to fruits or models. Effect of odor on propensity to alight on fruit or models and host-searching behavior prior to alighting on fruit or on models varied according to fruit or model color and density. If the fruit visual stimulus was strong (e.g., red color), odor did not increase the probability of finding fruit or fruit models. As the visual stimulus became progressively weaker (red to green to clear), odor (irrespective of concentration) appeared to aid flies during the fruit-finding process. As density of fruit or models increased, the probability of flies finding a fruit or model also increased (e.g., 50% of flies found a red fruit model at 1 model/tree while 90% found a red model at 16 models/tree; 4% of flies found a clear model with odor at 1 model/tree while 35% found a clear model with odor at 16 models/tree). Findings reported elsewhere indicate thatR. pomonella flies are able to discover a point source of odor (an odor-bearing tree in a patch of trees) by flying upwind (in the tree patch) in response to intermittent exposure to odor. Findings here indicate that after arrival on a host tree (point source), flies discover individual apparent and abundant host fruit on the basis of vision. If fruit are less apparent or scarce, odor appears to interact with vision during the fruit-finding process.     

基于HEIV模型的摄像机一维标定

多摄像机系统广泛应用于文化创意产业,其高精度标定是迫切需要解决的一个关键问题. 新近出现的摄像机一维标定方法能够克服标定物自身遮挡,特别适合标定多摄像机系统. 然而,现有的摄像机一维标定研究主要集中在降低一维标定物的运动约束,而标定精度较低的问题未受到应有的关注. 本文提出一种基于变量含异质噪声 （Heteroscedastic error-in-variables,HEIV）模型的高精度摄像机一维标定方法. 首先,推导出摄像机一维标定的计算模型;其次,利用该计算模型详细分析了一维标定中的噪声,得出摄像机一维标定可以视为一个HEIV问题的结论;最后给出了基于HEIV模型的摄像机一维标定算法. 与现有的算法相比,该方法可以显著改善一维标定的精度,并且受初始值影响小,收敛速度快. 实验结果验证了该方法的正确性和可行性.     

An open-source multi-DOF articulated robotic educational platform for autonomous object manipulation

This research presents an autonomous robotic framework for academic, vocational and training purpose. The platform is centred on a 6 Degree Of Freedom (DOF) serial robotic arm. The kinematic and dynamic models of the robot have been derived to facilitate controller design. An on-board camera to scan the arm workspace permits autonomous applications development. The sensory system consists of position feedback from each joint of the robot and a force sensor mounted at the arm gripper. External devices can be interfaced with the platform through digital and analog I/O ports of the robot controller. To enhance the learning outcome for beginners, higher level commands have been provided. Advanced users can tailor the platform by exploiting the open-source custom-developed hardware and software architectures. The efficacy of the proposed platform has been demonstrated by implementing two experiments; autonomous sorting of objects and controller design. The proposed platform finds its potential to teach technical courses (like Robotics, Control, Electronics, Image-processing and Computer vision) and to implement and validate advanced algorithms for object manipulation and grasping, trajectory generation, path planning, etc. It can also be employed in an industrial environment to test various strategies prior to their execution on actual manipulators.     

基于Hough圆卷积变换的孔组检测

为降低孔组测量的成本,提高测量的精确度,提出一种基于Hough国卷积的孔组检测方法.对孔组图像进行中值滤波、拉普拉斯锐化增强和边缘检测;根据孔组半径大小的变化范围,对Hough圆锥进行改进;在此基础上,利用改进的Hough圆锥与边缘检测后的图像进行三维卷积,得到Hough参数空间,计算出孔组的坐标和半径值;采用快速傅立叶变换法代替三维卷积,减少算法的计算时间.实验结果表明,该方法的检测精度高、实时性强,可以用于孔组的自动化检测.     

结构光视觉引导的焊接机器人系统自标定技术

为实现结构光视觉引导的焊接机器人系统的标定,解决现有标定方法复杂,标定靶标制作要求高等缺点,提出一种基于主动视觉的自标定方法。该标定方法对场景中3个特征点取像,通过精确控制焊接机器人进行5次平移运动,标定摄像机内参数和手眼矩阵旋转部分;通过进行2次带旋转运动,结合激光条在特征点平面的参数方程,标定手眼矩阵平移部分和结构光平面在摄像机坐标系下的平面方程;并针对不同焊枪长度进行修正。在以Denso机器人为主体构建的结构光视觉引导的焊接机器人系统上的测试结果稳定,定位精度可达到±0.93 mm。该标定方法简单,特征选取容易,对焊接机器人系统在实际工业现场的使用有重要意义。     

基于IMAQ Vision和PLC的水果大小自动分级系统设计

水果大小是水果分级的一个重要依据,随着计算机技术和图像处理技术的飞速发展,计算机视觉技术被广泛用于水果品质的检测。所设计的水果大小自动分级系统由机器视觉检测系统和基于PLC的水果传送分拣机构组成。使用LabbVIEW软件编写水果大小自动分级系统的监控界面,并实现对CCD摄像机的控制及获取图片;使用IMAQ Vision工具包对所获取的水果图片进行处理,并进行大小分析,根据大小的等级由LabVIEW通过串口通信发送命令给PLC,由PLC控制水果的传送并进入对应的分级口,从而完成水果的自动分级。实际运行证明该系统能实时进行动态采集图片,有效地进行水果大小分析及自动分级。     

一种基于增强现实的虚拟眼镜试戴的方法

选用单目的 CCD(Charge-coupled device)摄像头作为输入传感器,提出了一种基于标识物特征与人脸特征共同作用的增强现实技术设计并实现了一个虚拟眼镜试戴系统。通过单目摄像头采集现实场景的信息,对采集的图像进行分析,识别,并跟踪标识物与人脸特征,使虚拟眼镜模型可以准确地叠加在人脸之上,从而实现虚拟眼镜的试戴。实验证明,该方法可以准确地识别标识物,快速完成虚拟眼镜的试戴,为眼镜试戴技术提供了新的思路。     

基于全局和局部特征融合的显著性提取方法

显著性提取方法在图像处理、计算机视觉领域有着广泛的应用.然而,基于全局特征和基于局部特征的显著性区域提取算法存在各自的缺点,为此本文提出了一种融合全局和局部特征的显著性提取算法.首先,对图像进行不重叠地分块,当每个图像块经过主成分分析(Principle component analysis,PCA)映射到高维空间后,根据孤立的特征点对应显著性区域的规律得到基于全局特征的显著图;其次,根据邻域内中心块与其他块的颜色不相似性得到基于局部特征的显著图;最后,按照贝叶斯理论将这两个显著图融合为最终的显著图.在公认的三个图像数据库上的仿真实验验证了所提算法在显著性提取和目标分割上比其他先进算法更有效.     

基于机器视觉的转辙机缺口检测方法研究

针对现有转辙机缺口检测方法所存在的问题,本文介绍了一种基于机器视觉技术的转辙机缺口检测基本方法及其原理和步骤。文章详细论述了LSD算法的工作原理,同时本文作者对该算法做出了改进。最后将改进的LSD算法应用在转辙机缺口检测当中,结果表明该检测算法具有良好的稳定性和快速性,并且能够很好的解决转辙机缺口检测的问题。