12
vision award
communicate with other PLCs or cameras, to transfer inspection results for example. The camera is suitable for controlling small, autonomous production systems, such as servo-controllers using CANopen for (fine) positioning of axis or flexible gripping of parts. This leads to a reduction in system complexity and cost. An intelligent network of cameras can also be set up, with a master camera controlling other cameras in complex inspection tasks.
www.festo.com
PolKa – a robust, cost-effective, artefact-free solution for the analysis of polarised light Sean Durkin Fraunhofer Institute for Integrated Circuits IIS
The Fraunhofer Institute for Integrated Circuits IIS will present PolKa, an innovative camera for imaging polarimetry. PolKa uses a novel,
custom-made CMOS image sensor with integrated per-pixel polarisers. No external rotating polarisation filters or LCD shutters are needed; all polarisation information is captured in one single shot. Because of this, PolKa captures images free of motion artefacts and even supports high frame rates. Since no moving parts are used, PolKa is rugged and optimally suited to industrial applications. The polarisation filters are created as part of the CMOS fabrication process, so they will always be perfectly aligned to the pixels; no complicated calibration or set-up procedure is needed. This makes PolKa a robust, cost-effective, artefact-free solution for the analysis of polarised light. Applications include material testing, surface inspection, mechanical stress measurement and many more.
www.iis.fraunhofer.de
InspectOn Sensor – a surface defect detection system based on a neural network memory chip Thomas Woywod GlobalSensing
GlobalSensing’s InspectOn Defect Detection System (DDS) is a modular affordable system for the detection of anomalies in surfaces including glass and plastic, vinyl, wood, paper and pulp, fabrics, printing, and more.
The system is a chain of miniature trainable vision sensors (MTVS) mounted on a DIN-rail and spaced so their fields of view cover the entire width of the material under inspection. Each InspectOn sensor features a high- speed texture recognition engine based on a neural network chip. It is capable of learning a texture deemed ‘good’, whether smooth or patterned, and detecting anomalies as small as 2 x 2 pixels. This is all at high speed and with minimum constraints regarding the stability of lighting and possible contextual variations.
The modularity of the InspectOn DDS makes it easy to install and maintain. The training of the DDS is easy through the DDS Monitor software. The knowledge base of the representation of a ‘good’ material is built by selecting examples in images collected by the DDS sensors on the production line. Different knowledge bases can be built and saved per type of material, type of client, etc. Once all the sensors are loaded with a validated knowledge, they can inspect a full video frame in less than 75 milliseconds. The reporting of the anomalies then takes four microseconds per sensor over a serial line and this data can be processed by a controller interfacing with a marker, cutter or other equipment. Depending on the velocity of the material flow, the speed performance of the DDS may allow for multiple detections of an anomaly in the sensors’ field of view, thus reinforcing the robustness of the detection.
www.globalsensing.com
High-speed/high-precision 3D sensor with pixel-level signal processing and camera-level surface extraction Andreas Corliano, Yves Delley, Joël Forchelet, Christian Lotto, Patrick Lambelet, Rudolf Moosburger, Stephan Beer, Peter Seitz, Dino Zardet, Christa Zimmerli Heliotis
In the realm of industrial vision, the use of white light interferometry-based 3D measurement systems has so far been
limited. Long measurement times and a vulnerability to vibrations render standard interferometers incompatible with production requirements. Heliotis presents a high-speed, high-
precision 3D sensor based on parallel Optical Coherence Tomography (pOCT). The application-specific hardware acquires up to 90 billion samples of interferometry data per second and extracts surface maps in real time. This performance is achieved by implementation of a highly efficient two- step data reduction approach consisting of quadrature demodulation, signal integration, and down-sampling by each pixel of an application-specific ‘smart pixel’ imager chip, as well as surface extraction and transformation into accurate height map data by an application-specific FPGA-based smart camera. Production floor in-line testing applications can now benefit from the advantages of white light interferometry such as excellent resolution and highly robust detection over a wide variety of target geometries and materials.
www.heliotis.ch
Gocator: An all-in-one smart 3D sensor for easy measurement and control featuring a built-in web server, measurement tools, rich I/O, and an open source SDK Terry Arden LMI Technologies
The Gocator is a 3D smart sensor offering an all-in-one package to perform 3D measurement and control functions. The smart sensor provides quality results in
factory processes without requiring sophisticated machine vision experience. Gocator is pre-calibrated and can be set up to make measurements within minutes. With a suite of built-in visualisation and measurement tools, the smart sensor can be configured quickly with any web and setup on any operating system. Potential functions include performing cross-sectional or volumetric measurements, apply decision criteria, and communicate I/O to factory PLC networks. Built-in calibration means the sensor can be aligned to a reference plane (like a conveyor), handling common issues like offsets or tilt. Gocator offers a fluid and responsive setup environment for factory floor technicians to achieve advanced measurement, reliability, and stability in their processes.
www.lmi3D.com
imaging and machine vision europe october/november 2011
www.imveurope.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60