非接触式机器人直线轨迹测量系统

视觉的、造价低廉实用的非接触式机器人直线轨迹测量系统．该测量系统由结构光视觉传感 器、测量轨道、主控计算机及相关软件组成．视觉传感器可固定于机器人末端．当机器人末 端带动视觉传感器沿测量轨道做直线运动时，通过传感器测量相对测量轨道的连续位姿关系 ，就可间接描述机器人末端的运动轨迹．当重复同一直线运动时，可检测出机器人的轨迹重 复性．本文综述了机器人直线轨迹测量设备的研究现状，介绍了轨迹检测系统的测量原 理，重点讨论了该测量系统的两个关键技术：空间特征点的图象提取技术和三维坐标计算方 法，并描述了该系统的结构、性能指标和测量试验结果．     

Computer vision for human modelling and analysis

This report summarises the author's views and experience on the application of computer vision technology for the modelling and analysis of people. The author conducted research which led to the first commercial booth system for capturing animated models of people for applications in games, multimedia and virtual reality. This research is ongoing with the aim of developing studio capture technology to enable photo-realistic capture of a person's shape, appearance and movement for broadcast production.Published online: 8 August 2003     

A pipelined image analysis system using custom integrated circuits

The requirements of a computer vision system in relation to industrial applications are studied. It is concluded that for the iconic image-processing part, a pipeline system built around a custom integrated circuit is preferred. This custom integrated circuit makes it possible to realize four basic operations in a compact way: shape recognition, mask generation, programmable image delay, and subsample filtering. An example that has been processed by a hardware realization of such a pipeline system is provided     

基于ROS的机器视觉系统实现

Machine vision is used in industrial robot applications for industrial inspection, flaw detection, precision measurement and control, automatic production lines, medicine and various hazardous applications. Based on the open source robot operating sys- tem ROS, this paper uses Kinect binocular vision sensor to obtain 3D stereo vision data, and combines with OpenCV, OpenNI and other open source machine vision libraries to design a low-cost machine vision system using the auxiliary machine vision tools pro- vided by ROS. The experimental test is carried on the prototype.     

基于机器视觉的航空散热器智能定位钻孔技术

因某型航空散热器再制造的需要，需对产品大量的散热管进行重复的钻孔工作，为解决人工钻孔不便开发的问题开发出一种利用带机器视觉装置的工业机器人对散热器进行定位钻孔的技术。根据产品的特点选用了相应功能的工业机器人与机器视觉装置硬件，给出了智能定位钻孔系统的设计技术方案，建立了系统控制以及软件结构框架。通过最小二乘法对机器视觉采集的图像进行处理，给定了系统坐标标定的过程和方法,明确了机器人定位精度及视觉精度的计量方法。试验结果表明，该系统提高了钻孔效率和精度，可应用于实际生产。     

A vision guided robotic system for flexible gluing process in the footwear industry

This paper presents a novel gluing machine comprising a Cartesian robot and a vision system. The vision system enables the location and reconstruction of the shape of objects to be glued; the detected information is then used to plan the trajectory of the robot whose end-effector is a glue gun and to move the robot with an error suitable to industrial gluing operations.A calibration procedure that enables transforming coordinates between the robot frame and the vision system frame is described. The calibration considers several mechanical inaccuracies and its effectiveness was evaluated using error maps.In particular, the paper examines objects to be glued along their edges, as frequently occurs for fabrics, leathers, and shoe soles. For this, two procedures to plan the trajectories of the robot are proposed: the first is for objects that can be treated as flat 2D objects, that is, their height variation is negligible; the second procedure is for 3D objects, that is, those with significant height variation.Several applicative examples are reported to highlight the flexibility of the gluing process.     

Robust auto tool change for industrial robots using visual servoing

This work presents an automated solution for tool changing in industrial robots using visual servoing and sliding mode control. The robustness of the proposed method is due to the control law of the visual servoing, which uses the information acquired by a vision system to close a feedback control loop. Furthermore, sliding mode control is simultaneously used in a prioritised level to satisfy the constraints typically present in a robot system: joint range limits, maximum joint speeds and allowed workspace. Thus, the global control accurately places the tool in the warehouse, but satisfying the robot constraints. The feasibility and effectiveness of the proposed approach is substantiated by simulation results for a complex 3D case study. Moreover, real experimentation with a 6R industrial manipulator is also presented to demonstrate the applicability of the method for tool changing.     

Performance analysis and optimisation of shape recognition and classification using ANN

Machine vision systems are being increasingly used for sophisticated applications such as classification and process control. Though there is significant potential for the increased deployment of industrial vision systems, a number of important problems have to be addressed to sustain growth in the area of industrial machine vision. Artificial neural networks (ANNs) coupled with machine vision systems offer a new methodology for solving difficult computational problems in many areas of science and engineering. As a consequence, the research work presented in this paper investigates several novel uses of machine vision and ANNs in the processing of single camera multi-positional images for 2D and 3D object recognition and classification. Many industrial applications of machine vision allow objects to be identified and classified by their boundary contour or silhouette. Boundary contour information was chosen as an effective method of representing the industrial component, a composite signature being generated using vectors obtained from the generation of multi-centroidal positions and the boundary pixels.The composite signature can be re-sampled to form a suitable input vector for an ANN. Three different ANN topologies have been implemented: the multi-layer perceptron (MLP), a learning vector quantisation network (LVQ) and hybrid self-organising map (SOM). This method of representing industrial components has been used to compare the ANN architectures when implemented as classifiers based on shape and dimensional tolerance. A number of shortcomings with this methodology have been highlighted, most importantly the identification of a unique sequence start point, vital for rotation invariance. Another problem may arise due to the conflict between the inherent robustness of ANNs when dealing with noise, and classifying components which are similar but display subtle dimensional differences.     

基于ROS的智能工业机器人系统开发平台

目前,工业机器人对于机器视觉、自主路径规划等智能化功能需求日益增长.然而在传统工业机器人系统中添加智能化功能模块时需要修改大量的源码,浪费了人力和成本.本文提出的基于ROS的易扩展机器人系统开发平台,能为开发者开发智能工业机器人系统提供了方便.本平台分为服务器端和机器人端.将机器人端作为一级节点,与安装ROS的PC服务器端进行通信.机器人一级节点由二级功能节点与功能模块组成.根据此平台开发实现的JPB06六自由度工业机器人系统具有机器视觉、自主定位、语音控制等智能化功能,可以满足工业机器人对于智能化和实时控制的需求.     

Multi-modal defect detection of residual oxide scale on a cold stainless steel strip

This work presents two initial approaches and a novel technique for the industrial inspection of residual oxide scale on a cold stainless steel strip. The research aims to develop real-time systems to detect 50-μm defects. Initially, a spectrophotometric analysis provides the wavelength regions where differences between stainless steel and residual oxide scale reflectance are highlighted. The multi-modal approach is based on laser techniques that comprise three different strategies to gradually achieve a robust stainless steel industrial inspection through the evaluation of their performance. First, an inspection system based on a single commercial laser has been designed with a dynamic threshold module. In the second approach, the inspection task is accomplished by volatilizing a reduced area of the stainless steel surface with short pulses of a high-power ultraviolet laser and then analyzing the generated plasma with an intensifier camera. The third technique consists of an innovative smart vision system for surface visual inspection based on laser diode diffuse illumination. This vision system can be configured to work with two laser illumination modes: the diffuse coaxial lighting and the diffuse bright-field lighting. These techniques aim to gradually improve surface defect detection of a cold stainless steel strip. Furthermore, some of the results of the defect detection level obtained with each approach are displayed and discussed.     

Automated Processes in Digital Photogrammetric Calibration, Orientation, and Triangulation

Recent innovations in digital close-range photogrammetric systems for industrial applications have made possible a high level of automation within the 3D coordinate measurement process. This paper reviews innovations in automation for off-line vision metrology (VM) systems and discusses their operational impact. Concepts such as coded targets, exterior orientation devices, and robust solutions to the multi-image target point correspondence problem are illustrated through reference to a VM system capable of dimensional measurement accuracies of close to 1:200,000.     

基于机器视觉的五金件在线检测系统的设计

主要介绍了基于机器视觉检测技术在五金件检测系统中的应用,系统控制步进马达旋转,带动料带式的五金件前进,通过视觉成像装置（工业相机、镜头、光源）将产品形状转化为图像信号并传输到系统,系统进行图像处理,提取出需要产品轮廓并计算其尺寸数据。系统通过生产验证,取得良好的效果,具有一定的推广价值。     

DeViouS: A distributed environment for computer vision

Computer vision, owing to the size and complexity of its tasks and its importance to industrial and economic growth, was selected as one of the grand challenge problems by the U.S. Federal High Performance Computing Program. Integration of vision operations is identified as a key element of the challenge. A system to integrate computer vision in a distributed environment is presented here. This system, called DeViouS, is based on the client/server model and runs in a heterogeneous environment of Unix workstations. Modern computing environments include large numbers of high-powered workstations connected by a very fast network. Many of these computers are idle most of the time. DeViouS takes advantage of this feature of computing environments to distribute the execution of vision tasks. Two primary goals of DeViouS are to provide a practical distributed system and a research environment for vision computing. DeViouS is based on a modular design that allows experimentation in various aspects of algorithm design, scheduling and network programming. It can make use of any existing computer vision packages with very minor changes to DeViouS. DeViouS has been tested in an environment of SUN and Digital workstations and has shown substantial improvements in speed over sequential computing with negligible overhead.     

一种新的图象特征抽取方法

本文提出了一种新的特征抽取方法。它可对任意形状的工件进行准确描述，并具有计算速度快、特征抽取结果简单的特点。用此算法做成的视觉系统，能识别任意放置的甚至有遮挡或重叠的二维工件，是一种较好满足工业生产线上实时性要求的算法。     

机器视觉技术在工业中的应用

机器视觉为工业自动化提供了一种非接触的解决方案，在诸多领域可以有效取代并超越传统的人工或其它检测方法，实现整个自动化链的闭合。本文就工业机器视觉的系统构成、分类、开发现状与技术趋势进行了描述。     

浮选工业生产中的计算机视觉器

该项目是欧盟投资 130多万欧元的 3年研究项目。从 1997～ 2 0 0 0年 ,3个国家、4所大学和 2个企业 ,共 6个研究组共同进行了这一项目的研究工作。主要研究内容及路径 :(1)建立一个实时图象采集系统 ;(2 )图象处理及分割 ;(3)图象分析及矿物提炼的模型的建立 ;(4)用于工业生产自动控制。该项目的技术核心为如何以计算机视觉来代替人眼和人脑自动实时地观测浮选槽表面的变化 ,研究结果已很好地实现了这一技术。目前已有 13台系统被用于欧洲的选矿企业中     

壁面爬行遥控检查机器人控制系统的研制

本文介绍壁面爬行遥控检查机器人控制系统，该控制系统采用二级计算机控制。二极计算机之间采用光缆进行通讯，主计算机采有工业级ＰＣ总线计算机，从计算机采用ＳＴＤ总线计算机，主计算机能够对控制系统中的其他部分及视觉系统，检查系统和支持系统的行为进行协调和管理。     

基于粒子群算法的双目立体视觉系统标定

摄像机标定是立体视觉系统研究的重要组成部分,针对双目立体视觉系统中摄像机标定这一多参数、复杂函数的优化问题,建立带有一阶径向畸变的摄像机模型,利用粒子群算法对模型中的参数进行优化处理,并同改进遗传算法的优化结果进行比较分析。实验结果表明该方法具有较高的精度,可满足工业机器视觉的要求。     

计算机视觉控制系统在显象管灯丝二次绕线机中的应用

本文介绍一种基于图象处理和识别技术的计算机视觉控制系统。装有此系统的半自动化显象管灯丝二次绕线机,改造成全自动化的二次绕线机。这是机器视觉系统应用于工业生产的一个极好例子。