This article discusses inspection as a multi-disciplinary activity, involving mechanical handling (including robotics), illumination, optics, sensors, analog signal processing, digital electronics, computer system arc...
详细信息
This article discusses inspection as a multi-disciplinary activity, involving mechanical handling (including robotics), illumination, optics, sensors, analog signal processing, digital electronics, computer system architecture, software, and algorithms. Inspection systems design with the intention of integrating the system into existing quality assurance and manufacturing processes and practices are considered.
The proceedings contains 12 papers from the ieecolloquium on Underwater Applications of Image Processing. Topics discussed include: sidescan sonar survey data analysis;underwater robotics navigation using multisensor...
详细信息
The proceedings contains 12 papers from the ieecolloquium on Underwater Applications of Image Processing. Topics discussed include: sidescan sonar survey data analysis;underwater robotics navigation using multisensor fusion;behaviors implemented using a vision system based on coded light projection;broadband underwater acoustic communications systems;wide-band high-resolution sonar techniques;autonomous underwater vehicles as imaging platforms;automated acoustic data collection experiments using a directional projector system;uncalibrated computervision techniques in the underwater environment;and underwater measurement of salmon biomass.
The projected vast expansion in the robot population is based on two assumptions, firstly, that robot devices will drop sharply in price and secondly, that it will be possible to incorporate elements of artificial int...
详细信息
The projected vast expansion in the robot population is based on two assumptions, firstly, that robot devices will drop sharply in price and secondly, that it will be possible to incorporate elements of artificial intelligence at equally low cost. The use of robots at such low cost gives rise to the problem of application engineering. Just as computer literacy has rapidly grown in production engineering, robot literacy is now becoming very prevalent.
A requirement was seen for a vision system at a price compatible with simple educational robots. The system described here is to be marked at under POUND 50. In addition to educational uses, it has already aroused int...
详细信息
A requirement was seen for a vision system at a price compatible with simple educational robots. The system described here is to be marked at under POUND 50. In addition to educational uses, it has already aroused interest as a simple addition to industrial robots. An 'eye-in-hand' sensor inspects only one point of the field of view;the system relies on the robot itself to scan the detector in a chosen manner. For simple educational use, a raster movement can be used, the image being built up on a display screen. For more serious applications, edge search and following strategies allow the location and identification of objects. For industrial use, this form of primitive vision provides back-up in a fault condition, allowing a search to be made for a slightly misplaced object or location. In its simplest form a single bit provides a comparison of point brightness against a manually set potentiometer. With the addition of one further output bit from computer to sensor, the system has been adapted to resolve over 200 levels of brightness on a logarithmic scale.
Progress in providing the Oxford Autonomous Guided Vehicle (AGV) with computervision capabilities is described. The GEC Turtle vehicle is the basis for a sensor integration project in which vision plays the strategic...
详细信息
Progress in providing the Oxford Autonomous Guided Vehicle (AGV) with computervision capabilities is described. The GEC Turtle vehicle is the basis for a sensor integration project in which vision plays the strategic role of locating pallets in an unstructured environment. In other projects, the aim is visual servocontrol of the vehicle. Early visual processing using a Sun/Datacube architecture is sketched. Model-based recognition of palletised loads is discussed. Finally, work on the development of parallel vision algorithms is reviewed.< >
Provision is a computer language, currently under development, for use as a development tool in automated visual inspection and robot vision. It is a superset of PROLOG, and its syntax is the same as that of PROLOG. I...
详细信息
Provision is a computer language, currently under development, for use as a development tool in automated visual inspection and robot vision. It is a superset of PROLOG, and its syntax is the same as that of PROLOG. It uses the same control mechanisms namely backtracking and recursion. It also provides facilities for the matching and unification of general data items, exactly as PROLOG does. There is a rich repertoire of image processing facilities in Provision. The control of electromechanical devices, such as lamps, lenses, cameras, (X,Y)-tables etc. follows the same convention as image processing. There is a large library of predicates for medium and high level image processing. It is currently implemented within a powerful environment, which provides pull-down menus. Applications are discussed, and a sample program is given.< >
Describes a transputer array system developed under the Alvey ParSiFal project and used for vision processing in a SERC/ACME project on automatic robotic assembly as well as for research into speech recognition. The t...
详细信息
Describes a transputer array system developed under the Alvey ParSiFal project and used for vision processing in a SERC/ACME project on automatic robotic assembly as well as for research into speech recognition. The transputer array of 't-rack' consists of 64 T800-20 transputers, each with 1 MB of memory and each with two links daisy-chained to the SUN host via a 'Tadpole Board' controller for program down-loading and data transfer. The other links of each transputer are taken to two cross bar switches for configuring the array. In some applications OCCAM is used but much of the work uses C and the system is networked under Unix. In the vision work data is acquired by a VME-based framestore unit (Seescan Imaging) at 8*512*512 resolution and transferred to the t-rack by a VME/DMA to transputer link card. This fans the input data stream out to 4 links and achieves a data rate of 6 frames per second. Two vision processing applications are presented.< >
暂无评论