Search results

Description of current 4DI three dimensional imaging system, a proprietary 3D vision sensing technology available from Intelligent Automation (IA), and introduction to the recently developed, next generation, HiPART (High‐resolution Phase Angle Resolved Triangulation) gauge sensor developed by a consortium in which IA participated. Both are non‐contact electro‐optical systems capable of being applied to a wide realm of inspection possibilities for the metrology industry. The HiPART sensor is one of the key non‐contact measurement technologies developed by potential end‐users of the technology, high‐technology advancement companies, and the US government in a collaborative effort to improve the measurement and inspection processes of manufactured parts. Specifications and benefits of the sensors, and examples of possible uses are outlined, illustrating the advantage that the 4DI and HiPART sensor have over standard coordinate measuring machines (CMMs). These sensors are actively being commercialized by IA, a custom automation and machine vision development company, which is introducing it to the appropriate markets.

Describes a three‐dimensional machine vision technology for inspecting and measuring on‐line production. States that the 4DI three‐dimensional imager, a new machine vision technology developed by Intelligent Automation Systems, combines speed and accuracy to perform 100 per cent on‐line inspection and measurement of volumes and surfaces in real‐time. Until recently, neither conventional measurement techniques such as co‐ordinate measurement machines nor non‐contact optical technologies could inspect 100 per cent of production on‐line three‐dimensionally, being either too slow or too sensitive to ambient light. The 4DI uses structured laser light, multiple cameras and triangulation to capture moving or stationary objects. States this technology allows objects of different sizes, ranging from several feet to fractions of an inch to be imaged. States the system has no moving parts, it is robust in industrial environments.

A report on the vision systems featured at the new TEAM exhibition. The products and applications of three companies are highlighted. Two exhibitors have contrasting approaches to the application of vision: DVT takes the integrated route with “all in” intelligent cameras while Data Translation follows the PC‐based philosophy with separate frame grabbers. The third company discussed is Leica Geosystems and its laser tracker mobile measurement systems used for inspection of large components as well as the control and calibration of robots, machine tools and the like. Leica introduced a new handheld probe for inspecting deep cavities and a new laser radar system that, unlike the tracker, needs no reflectors mounted on the object under inspection.

Technological advances in recent years have led to the development and implementation of a variety of techniques and platforms in three‐dimensional (3D) metrology. These techniques include improvements in sensory capabilities, computational speed, flexibility in reporting, and ease of use. The purpose of this paper is to address several developments in this regard.

Metrology, or the science of measurement, continues to enjoy relevance and importance in the quality and handling of manufactured goods. In most instances, measurement requires a 3D quantification of an object's dimensions. These data are used for product quality or for robotic guidance applications.

As technology progresses, a snapshot of trends is presented in 2009. Notable amongst these trends are advances in sensory capabilities, computational speed, flexibility in reporting, and ease of use. These continuous improvements are helping to increase adoption curves in an ever‐competitive quality and cost driven, and increasingly international, manufacturing market. According to Paul Kellett, Director of Market Analysis at the Robotics Industries Association (www.robotics.org), there have been, in the past, typically three impediments to adoption: ease of use, cost, and performance of technology.

In conclusion, metrology and 3D trends are evolving continuously to equip manufacturers with enhanced tools for measurement, quality control, robot guidance and absolute accuracy. Much work lies ahead in the area of software for applications and specifically for vertical applications.

Optical measurement sensors are increasingly available, often finding application in measurement and inspection of manufactured products. For example, theodolites and laser trackers are already used to calibrate jigs and tooling. Digital photogrammetry is used in dimensional inspection of assemblies such as aircraft wings. Such tasks demand high performance sensors with 2D and 3D capability, large working envelopes, high accuracy, low measurement latency and increased flexibility. The availability of sensors which meet and exceed such criteria is fuelling new possibilities in the manufacturing process itself. Fixed tooling may be eliminated and replaced by flexible fixturing under the control of embedded sensor systems. Sensor technology is reviewed and a novel application presented.

Despite the influx of companies and systems offering automatic inspection for the PCB industry, its acceptance rate in Europe has been slow. The problem seems to be lack of machine intelligence and inflexibility—factors that European companies cannot tolerate due to the nature of the market and the product mix. A new optical inspection system based on the ‘comparison’ method offers the required flexibility, but has needed a great deal of research into mechanics, electronics and software to overcome inherent problems. As this programme nears completion, a new generation of automatic optical inspection and statistical control systems will be possible.

This paper aims to review the use of imaging technologies in robotics, with an emphasis on inspection applications and the control of autonomous robots.

Following a brief introduction, this paper first considers vision‐based robotic inspection systems and highlights a selection of recent applications. Second, it considers the use of vision in autonomous robot navigation and discusses some of the challenges and recent developments.

This shows that developments in machine vision have led to vision systems being used in a diversity of component‐level and in‐service robotic inspection tasks. It also illustrates that vision systems have a key role to play in the emerging generation of autonomous, mobile robots.

This paper provides a review of recent developments in vision‐based robotic inspection and autonomous, mobile robot navigation.

To show how advances in machine vision technology are of particular benefit to automated assembly.

The review concentrates on algorithms, cost effectiveness, and communications aspects of currently available commercial systems.

Vision is now very robust, affordable, and capable of being used at every stage in the assembly process.

The vision industry continues to evolve at a rapid pace and readers who may have been disappointed when they investigated the technology only a few years ago should learn how today's systems have improved.

The purpose of this paper is to explore the role that computer vision can play within new industrial paradigms such as Industry 4.0 and in particular to support production line improvements to achieve flexible manufacturing. As Industry 4.0 requires “big data”, it is accepted that computer vision could be one of the tools for its capture and efficient analysis. RGB-D data gathered from real-time machine vision systems such as Kinect ® can be processed using computer vision techniques.

This research exploits RGB-D cameras such as Kinect® to investigate the feasibility of using computer vision techniques to track the progress of a manual assembly task on a production line. Several techniques to track the progress of a manual assembly task are presented. The use of CAD model files to track the manufacturing tasks is also outlined.

This research has found that RGB-D cameras can be suitable for object recognition within an industrial environment if a number of constraints are considered or different devices/techniques combined. Furthermore, through the use of a HMM inspired state-based workflow, the algorithm presented in this paper is computationally tractable.

Processing of data from robust and cheap real-time machine vision systems could bring increased understanding of production line features. In addition, new techniques that enable the progress tracking of manual assembly sequences may be defined through the further analysis of such visual data. The approaches explored within this paper make a contribution to the utilisation of visual information “big data” sets for more efficient and automated production.