An In-Camera Data Stream Processing System for Defect Detection in Web Inspection Tasks

One of the aims of industrial machine vision is to develop computer and electronic systems to replace human vision in quality control of industrial production. Traditionally these systems consist of a line scan camera, host computer, frame grabber and one or more dedicated processing boards. In this paper we discuss the development of a new integrated design environment, developed for real-time defect detection, that eliminates the need for an external frame grabber and other associated host computer peripheral systems. The processing board contains a reconfigurable field programmable gate array FPGA inside a DALSA CCD camera. The FPGA is directly connected to the video data-stream and outputs data to a low bandwidth output bus. The system is targeted for web inspection but has the potential for broader application areas. We describe and show test results of the in-camera prototype system board and discuss some of the algorithms currently simulated and implemented for web inspection applications.     

基于机器视觉的机械手装配系统设计

为了解决工业生产过程中料板的自动装配问题,提出了一种基于机器视觉的机械手定位装配检测系统,建立了实验平台。系统通过工业相机对料盘进行图像采集,将所采集的信息传送给工控机,借助图像处理程序,采用图像预处理实现了对图像的降噪,结合BLOB分析对图像特征进行了提取,获得了料盘上装配孔的位置信息,通过控制机械手动作,移动到装配位置,旋转相应角度,实现料板的自动定位装配。实验结果表明,该系统装配准确度高,误差小,满足了工业上的要求。     

Design and evaluation of a versatile single board computer for embedded applications in scientific instrumentation

A single board computer has been developed for embedded applications in scientific instrumentation. The single board computer developed can be used for various purposes in scientific laboratories for instrument control and data acquisition. An application of the single board computer to a photodiode array detector system for liquid chromatography is described.     

某型舰炮随动系统数字化改进研究

针对某型舰炮随动系统进行数字化改进,设计了一种基于计算机的数字随动系统。本设计利用TMS320F2407电机控制芯片,独立输出两路PWM控制信号,分别驱动高低和方位两个执行电机。功率放大电路采用IPM模块组成的H桥结构。试验表明,该数字随动系统工作可靠、动态响应快、噪音低。     

微型直升机自主飞行辅助视觉系统研究

为了实现微型直升机自主飞行,论文设计了实时的计算机视觉系统。该系统包括机载上的硬件设备和软件算法,能够实现目标识别、特征点提取和位置估计。文中设计了特定图标,并主要依据颜色来进行快速识别。此外,通过检测4个共面的图像特征点,能够在单目单帧的基础上计算出直升机相对于特定目标的三维位置信息。视觉系统任务由位于机载上的IntelSitsang板来执行。由于受到板子运算能力的限制,每秒钟可以处理5帧160×120的彩色图像。飞行实验结果表明,该视觉系统的目标识别率高达93%,角点计算偏差小于3个像素,同时自身定位的三维位置坐标平均偏差为8cm、13cm和6cm。因此,该视觉系统通过精确自身定位,能够很好的辅助微型直升机完成自主悬停、起飞和降落等飞行任务。     

Robust strategies for diagnosing manufacturing defects

We describe several strategies used by expert troubleshooters performing a manufacturing screening task, the diagnosis of defects on a computer board. These strategies use "inexact models" of the components and connections on the board. A prototype expert system has been implemented that uses the strategies and models. The strategies and models are robust because they are applicable to a wide range of problems, including problems not previously encountered. The system saves useful data acquired during problem solving to assist in future problems. We also describe how the above strategies and models can be used in a sensorbased system that acquires information about the board through a vision camera and other sensing devices. This will further increase the productivity of human troubleshooters.     

全方位三维显著空间系统

图像的显著性分析是计算机视觉的一个重要研究方向。鉴于现有方法主要集中于对单幅图片进行显著分析,缺乏连续的、摄像头可动的显著图的深入研究。本文受到人类视觉系统的启发,设计了全方位三维显著空间系统。该系统使用提供摄像头方向信息的球形摄像机,将每帧图片的显著区域映射到显著空间中,并对映射结果进行简明有效的显示。本文详细介绍了该系统的组成框架和显著空间映射方法。通过测试验证,该系统具有良好的实时性,并成功实现了目标设计功能。     

基于PowerPC处理器的机载多总线单板计算机设计

为满足面向综合化飞行器管理平台的分布式控制需求,设计一种基于PowerPC处理器的机载多总线单板计算机,其以PowerPC8245处理器为核心,外部总线接口包括ARINC659总线、HB6096总线、GJB289A总线等多种机载总线接口。各总线接口依据其带宽、完整性要求、协议复杂程度等来采用不同的智能化处理方法,实现了外部总线接口的自主处理,避免了慢速的外设占用处理器资源,既完成了接口数据处理,又释放了处理器的处理能力。计算和接口的解耦使得PowerPC8245处理器可以作为计算机系统的主处理器使用,经过使用验证,可满足要求。该单板计算机也适用于综合化飞行控制的分布式控制系统。     

嵌入式人脸检测系统设计

介绍了以计算机视觉为背景,基于FPGA实现嵌入式人脸检测系统的设计。系统设计过程包括配置MicroBlaze软核处理器、裁剪μClinux内核和应用程序设计3部分。以MicroBlaze软核为处理核心,通过片内添加外设接口和IP在Virtex-ⅡPro开发板上搭建硬件平台。以μClinux内核为软件平台,通过优化OpenCV提供的源代码设计人脸检测应用程序。     

Model-based inspection system for component boards

A computer vision system has been developed to perform the complex inspection of many components on a flat surface or board. It has a hierarchical structure which allows it to determine the location of components with one camera resolution and then to inspect for small details with a higher resolution. The system has generality in that the same program can be used to inspect boards with completely different components by forming a new model. The MODEL-FORMER program carries out an interactive session with an operator who specifies the layout of components, showing the system each different component and selecting inspection tests which apply to specific regions of the component. These tests allow the INSPECTOR system to differentiate between good and bad components. During inspection, the system (using gray-scale rather than the more limited binary techniques) automatically inspects all components on the board for: (1) presence of correct component; (2) correct position and orientation; (3) any other important features which the operator has designated.     

单板计算机控制直流电动机可逆调速系统

本文叙述了单板计算机控制的直流电动机可逆调速系统.本系统用计算机软件代替原模 拟系统中的PI调节器、逻辑切换装置及其它模拟硬件,使可控硅触发器的输出数字化,从而实 现了全数字化控制.本系统不仅节省大量硬件,且调整方便,运行可靠性大为提高.     

Model-based visual feedback control for a hand-eye coordinatedrobotic system

The integration of a single camera into a robotic system to control the relative position and orientation between the robot's end-effector and a moving part in real time is discussed. Only monocular vision techniques are considered because of current limitations in the speed of computer vision analysis. The approach uses geometric models of both the part and the camera, as well as the extracted image features, to generate the appropriate robot control signals for tracking. Part and camera models are also used during the teaching stage to predict important image features that appear during task completion     

啤酒发酵全系数自适应控制

笔者运用吴宏鑫提出的全系数自适应控制方法及经验公式[1],1),对啤酒发酵温度进行控 制.文章给出了这一具有滞后特性的全系数自适应控制系统,并对经验公式进行了简化,以便 在单板计算机上简单地实现.该系统已用于石家庄啤酒厂露天发酵罐,并获得成功.     

Fuzzy image processing scheme for autonomous navigation of human blind

The main objective of this work is to develop an electronic travel aid to assist the blinds for obstacle identification in their navigation. This navigation assistance for visually impaired (NAVI) system presented in this paper consists of a single board processing system (SBPS), a vision sensor mounted headgear and a pair of stereo earphones. The image environment in front of the blind is captured by the vision sensor. The image is processed by a new real time image processing scheme using fuzzy clustering algorithms. The processed image is mapped onto a specially structured stereo acoustic patterns and transferred to the stereo earphones in the system. Blind individuals were trained with NAVI system and tested for obstacle identification. Suggestions from the blind volunteers regarding pleasantness and discrimination of sound pattern were also incorporated in the prototype. The proposed processing methodology is found to be effective for object identification and for producing stereo sound patterns in the NAVI system.     

Transputer application to speech recognition

Use of the architectural features of transputers to provide realtime matching of speech recognition is considered. The dynamic time warping algorithm has been implemented in occam and tested initially for matching a single word against a single template. The implementation has been extended to the multitemplate case and preliminary results for this are given. Logical extension to a multitransputer system is also discussed. The single-transputer implementation has been undertaken using a T414 transputer resident in an IBM XT personal computer on an Inmos B004 evaluation board with 2 Mbyte of RAM.     

基于DVT技术快速构建计算机视觉系统

计算机视觉技术利用信号处理和计算机技术实现信息处理的全过程,已经在多个领域得到了广泛的应用.然而由于视觉处理问题的多样性、复杂性,对计算机视觉处理系统的研究和开发提出了很高的要求.DVT计算机视觉系统作为嵌入式视觉软件中典型的一种视觉产品,具有非常强大的功能和良好的性价比.通过对DVT视觉的深入研究和学习,提出了实际应用中快速构建计算机视觉系统的方法和策略,系统所具有的功能、布局等对建立具有自主知识产权的视觉产品具有重要的参考价值.     

An integrated vision system based on coining algorithms

This article describes an integrated computer vision system that is based on the principle that improved function can better be achieved by combining weak and idiosyncratic operators than by striving to “fine-tune” a single operator. This binding or fusional principle emerged during the past decade of research on organic systems. The system combines many of the attributes of a visual image to segregate three-dimensions in a way that overcomes the deficiencies that have long been known to hamper computer image processing. The system can be applied to object detection and recognition, autonomous control, and manufacturing inspection.     

基于LabVIEW的航空发动机电子控制器检测系统的开发与应用

通过研究某型航空发动机电子控制器(EEC)的调节程序和接口关系,分析发动机使用中检测的需求,开发了外场在线检测系统.该系统运用LabVIEW软件开发平台,以平板电脑为核心,结合试车数据库,可以完成航空发动机性能曲线的录取和EEC的功能测试.     

基于早期视觉的算法模型评述

计算机视觉与神经生理学相结合,早期视觉模型与计算相结合,对视觉研究领域具有深远的意义.早期视觉研究处理的视觉信息是视觉系统接受信息的第一步,是视觉研究的基础.它用计算机视觉的实现方式,模拟了视锥通路的早期视觉信息处理模型,验证了生理视网膜在信息处理过程中的特性,分析了视觉神经在信息采集必须充分必要的条件下,硬件复杂度、处理时间与处理精度之间的平衡.