A 3-D vision system model for automatic object surface sensing

The development of a noncontact light striping (structured light) based three-dimensional, six-degrees-of-freedom vision system for automatic object surface sensing is reported. The system modeling and world-point reconstruction methodology involve homogeneous-coordinate system transformations applied in two independent stages: the video imaging stage using three-dimensional perspective transformations and the mechanical scanning stage using three-dimensional affine transformations. Concatenation of the two independent matrix models leads to a robust four-by-four, six-degrees-of-freedom system model. The reconstructed sectional contours are registered automatically in real time with respect to a common world-coordinate system as a control net for Non-Uniform Rational B-spline (NURBS) surface approximation. The reconstruction process is demonstrated by measuring the surface of a 19.5×2 ft rowing shell. A detailed statistical accuracy and precision analysis shows an average error of 0.2% (0.002) of the camera's field-of-view. System sensitivity analysis reveals a nonlinear increase of sensitivity for angles higher than 45° between the normals of the image and laser planes.     

基于视觉引导的SCARA机器人自动装配系统

现有生产线工业机器人抓取点固定,工件只能以固定的姿态提前摆放在固定的位置,这种装配模式很难满足复杂的工业生产要求且效率低下。设计了基于视觉引导的机器人装配系统改进原有系统。设计了机器视觉系统,实现了工件的快速识别、定位以及姿态确定功能;设计了抓放系统,实现了工件的精确抓取和安装功能;采用Visual Studio的MFC开发,实现图像处理算法,并利用Socket通信将坐标和姿态数据发送给机器人。通过实验验证本系统具有良好的稳定性和快速性,可以满足生产的要求,大幅提高生产效率。     

基于计算机视觉的织物疵点自动检测

介绍了基于计算机视觉的织物疵点自动检测的工作原理;分析了织物疵点自动检测的功能结构和自动检测硬件组成框图;阐述了织物疵点图像的半阈值化处理、边缘检测和疵点特征求取方法;给出了织物疵点自动检测的程序框图、织物疵点的坯布图像及其疵点统计结果。     

基于视觉传感的嵌入式自动读尺系统

介绍了一种基于机器视觉与嵌入式技术的直尺自动读数系统的设计方法。系统以32位ARM9微处理器S3C2440为核心,结合WINCE 5．0嵌入式操作系统,使用Embedded Visual C＋＋4．0软件开发平台,实现了对直尺的图像采集、处理与显示;算法部分通过改进的特征法对尺上数字字符进行精确识别,并读出视场中心刻线位置从而给出精确读数结果。实验结果表明：该系统具有高速度、高精度、稳定性好等特点,提高了测量的可靠性、准确度及自动化程度。     

An automatic aperture detection system for LED cup based on machine vision

In order to improve the effectiveness of aperture detection and enhance the competitiveness of enterprise, an automatic inspection system for detecting the aperture of Led cup is developed in the paper. The proposed system can achieve detecting the aperture and separating the unqualified Led cups robustly. Specifically, efficient approaches based on three-point circle fitting and convolutional neural network (CNN) are proposed to achieve automatic aperture detection. Then, a novel control unit is designed to separate the unqualified Led cups using the gas claw and air cylinder. Experimental results demonstrate that the detecting accuracy of the developed system can well meet the requirements of manufacturing enterprise. Moreover, the proposed system can greatly save time and labor costs for enterprises. In addition, with this system we can efficiently construct a vision big data of LED cups. Using such a vision big data, problems of the production line can be timely discovered, and the production quality will be greatly improved.     

基于机器视觉的荧光磁粉自动检测系统设计

现有荧光缺陷检测技术主要采用人眼视觉判定与半自动化等方式,针对目前存在的检测效率低、对人体辐射损伤大等问题,提出一种基于机器视觉的荧光磁粉自动检测流水线系统。该系统具备自动磁化、缺陷检测及智能分拣等功能,实现检测过程的全自动;采用基于梯度聚类算法的磁痕缺陷识别方法,可根据缺陷特征进行检测模式分类,以提高缺陷检测的准确性。实验结果表明:该系统实现工件缺陷的全自动化检测,平均识别正确率高达98. 53%,检测效果较好,具有较高推广价值。     

A hierarchical multiple-view approach to three-dimensional objectrecognition

A hierarchical approach is proposed for solving the surface and vertex correspondence problems in multiple-view-based 3D object-recognition systems. The proposed scheme is a coarse-to-fine search process, and a Hopfield network is used at each stage. Compared with conventional object-matching schemes, the proposed technique provides a more general and compact formulation of the problem and a solution more suitable for parallel implementation. At the coarse search stage, the surface matching scores between the input image and each object model in the database are computed through a Hopfield network and are used to select the candidates for further consideration. At the fine search stage, the object models selected from the previous stage are fed into another Hopfield network for vertex matching. The object model that has the best surface and vertex correspondences with the input image is finally singled out as the best matched model. Experimental results are reported using both synthetic and real range images to corroborate the proposed theory.     

A knowledge-based vision system for industrial applications

This paper introduces a knowledge-based vision system for industrial environments. It is designed to control a cell in an assembly system. The images from the environment are taken as gray scale images. Based on a single image, the system has to recognize type and position of the recorded parts and to control their placement in the environment for further manipulation. This requires the explicit representation of rich task-specific knowledge. The effort to adapt our system to new tasks is very small. Thus, it is very important that the system is able to support major parts of the activities that are necessary for the acquisition of new knowledge. The system consists of three components-image segmentation, knowledge acquisition, and matching-which are described in detail. All the methods presented were tested using different parts of an electric motor as an example.     

A retinomorphic vision system

This system uses neurobiological principles to accomplish the major operations of biological retinae: continuous sensing, local automatic gain control, spatiotemporal bandpass filtering, and adaptive sampling     

Expert system design for vacant parking space location using automatic learning and artificial vision

Multimedia Tools and Applications - Finding a free parking space nowadays is a recurring problem in increasingly crowded public parking lots. The present study offers a solution that is based on...     

基于机器视觉的全自动电池检测系统的研究

给出了一种基于机器视觉和X射线的全自动电池检测系统.利用X射线的穿透性和计算机对数据的快速处理能力,相机可以采集到成型电池的内部结构图像并对图像数据进行快速处理.通过对图像进行滤波、锐化、边缘提取等过程得到阴极和阳极的精确位置.运用软件来测量各个特征问的距离并与标准值进行比较来判断电池的好坏,从而实现电池检测过程的完全自动化操作.     

基于计算机视觉的烟叶自动分级系统硬件设计

介绍了一种基于计算机视觉烟叶自动分级系统的硬件组成,该系统由输送装置、称重系统、视觉系统、均匀照明室4部分组成。输送装置可将烟叶打散摊平,使烟叶保持一定的厚度呈现给CCD摄像头;称重系统采用电子皮带秤完成烟叶的在线实时称重,并将数据发送至计算机内存;视觉系统同时监视、采集烟叶图像信息送至计算机内存进行处理;照明系统为CCD摄像头均匀、恒定的光源,保证图像的清晰。实验证明了系统的可行性,其辅助机构与烟叶实时分级决策算法尚待进一步的研究。     

单目视觉在棒料全自动上下料系统中的应用

在全自动上下料系统中,机器视觉技术以它快而准确无误的性质发挥重要的作用.针对系统的功能要求,进行了基于单目视觉全自动上下料系统平台的设计和搭建,通过Halcon完成了摄像机和机械手标定,理论上研究了实现空间棒料的三维姿态的算法,在图像处理中运用二项式滤波、傅立叶变换、闵可夫斯基加减法确定空间棒料的三维姿态,通过VS2015C#与Halcon混合编程,进行软件界面开发,控制机械手上下料.结果表明该方法具有可行性.     

Coarse-coded higher-order neural networks for PSRI objectrecognition

The authors describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096x4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, the authors empirically determine the limits of the coarse coding technique in the position, scale, and rotation invariant (PSRI) object recognition domain.     

A rule-based system for automatic seismic discrimination

This paper proposes a rule-based system for automatic seismic discrimination, i.e. classification of earthquakes and underground nuclear explosions. It incorporates rule-based deduction, pattern recognition and signal processing for an effective identification. The seismological knowledge and heuristics are represented by a set of production rules. Facts and assertions of the production rules are derived from seismic signals using signal processing and pattern recognition methods. Due to the uncertainty nature of this problem there are certainly factors associated with both antecedents and the rules. The control strategy is data-driven, i.e. forward-chaining for better efficiency. This approach can be applied to other signal and image interpretation problems.     

A framework for automatic DFA system development

Deisgn for assembly (DFA) evaluation has proved to be a systematic approach is determining how well a product is designed from an assembly point of view. Proposed here is a framework for automating DFA evaluation procedure, a key step in achieving a concurrent design environment. Five modules required for this development are: assembly sequence generation; assembly features extraction; assembly code and other necessary operations generation; data manipulation and computation; and re-design suggestion. Partial implementation (linking DFA evaluation procedure with a feature based CAD system) of the framework is also presented.     

A vision system for robotic inspection and manipulation

A model-based approach has been proposed to make object recognition computationally tractable. In this approach, models associated with objects expected to appear in the scene are recorded in the system's knowledge base. The system extracts various features from the input images using robust, low-level, general-purpose operators. Finally, matching is performed between the image-derived features and the scene domain models to recognize objects. Factors affecting the successful design and implementation of model-based vision systems include the ability to derive suitable object models, the nature of image features extracted by the operators, a computationally effective matching approach, knowledge representation schemes, and effective control mechanisms for guiding the systems's overall operation. The vision system they describe uses gray-scale images, which can successfully handle complex scenes with multiple object types     

A vision system for an underwater cable tracker

Nowadays, the surveillance and inspection of underwater installations, such as power and telecommunication cables and pipelines, is carried out by operators that, being on the surface, drive a remotely operated vehicle (ROV) with cameras mounted over it. This is a tedious and high time-consuming task, easily prone to errors mainly because of loss of attention or fatigue of the human operator. Besides, the complexity of the task is increased by the lack of quality of typical seabed images, which are mainly characterised by blurring, non-uniform illumination, lack of contrast and instability in the vehicle motion. In this study, the development of a vision system guiding an autonomous underwater vehicle (AUV) able to detect and track automatically an underwater power cable laid on the seabed is the main concern. The vision system that is proposed tracks the cable with an average success rate above 90%. The system has been tested using sequences coming from a video tape obtained in several tracking sessions of various real cables with a ROV driven from the surface. These cables were installed several years ago, so that the images do not present highly contrasted cables over a sandy seabed; on the contrary, these cables are partially covered in algae or sand, and are surrounded by other algae and rocks, thus making the sequences highly realistic. Accepted: 13 August 2001     

A rule triggering system for automatic text-to-sign translation

The topic of this paper is machine translation (MT) from French text into French sign language (LSF). After arguing in favour of a rule-based method, it presents the architecture of an original MT system, built on two distinct efforts: formalising LSF production rules and triggering them with text processing. The former is made without any concern for text or translation and involves corpus analysis to link LSF form features to linguistic functions. It produces a set of production rules which may constitute a full LSF production grammar. The latter is an information extraction task from text, broken down in as many subtasks as there are rules in the grammar. After discussing this architecture, comparing it to the traditional methods and presenting the methodology for each task, the paper present the set of production rules found to govern event precedence and duration in LSF and gives a progress report on the implementation of the rule triggering system. With this proposal, it is also hoped to show how MT can benefit today from sign language processing.