Image processing system

from Wikipedia, the free encyclopedia
This article or section needs to be revised. Details should be given on the talk page. Please help to improve it , and then remove this flag.

Image processing systems can be used practically anywhere these days. If a visual feature can be recorded by an image recording (camera, scanner), the machine image processing can check, compare, measure and verify it. The image processing systems are used in automated production, robot control and quality assurance. Image processing systems are also used in other areas such as remote sensing , medicine , security and traffic engineering . As before, a BVS is not an off-the-shelf product for most applications, but requires application-specific adaptation.

Responsibilities of the BVS

The tasks of the image processing systems include:

  • handling (automatic tracking of tools such as welding electrodes, screwdrivers, drills; especially in the automotive industry)
  • the identification of workpieces
  • the implementation of test and measurement tasks in production / quality control
  • the monitoring of facilities, rooms
  • the image enhancement,
  • image reconstruction ( computed tomography )
  • understanding the image

How the BVS works

The operation of an image processing system includes:

  • the image recording with camera, optics and lighting,
  • the digitization of data,
  • the search for the essential features,
  • the interpretation of the results,
  • the reaction with the regulation of the machine.

Lighting for the BVS

Lighting method

A basic requirement for the correct functioning of the system is the correct lighting arrangement. The luminaire can be used in the incident light method (camera and light source are on the same side of the feature) or in the transmitted light method (light source is behind the feature). Using light, shadow, reflections and interference patterns, the features to be checked can be highlighted in such a way that the evaluation does not cause any problems.

Alignment of lighting and camera (production)

Each camera looks at a specific feature on the workpiece. Such features can be holes, corners or other two-dimensional uniquely localizable features. In order to enable the workpiece to be picked up correctly, the features viewed by the cameras must be as close as possible to the grippers. It is also advantageous if the features are as far apart as possible. This means that small measurement errors are less noticeable. The accuracy of the system also depends heavily on the size of the field of view of the cameras. The smaller the field of view of the cameras and thus also the search area, the more precise the end result will be. The image field size must be set up in such a way that the selected features fit into the image, taking into account the uncertainty of the pre-positioning of the workpiece with a small allowance.

Adjustment and workpiece removal with the help of the BVS (production)

The positional deviation of the workpiece is determined by comparing the position of a target pattern with the existing workpiece and the robot path is corrected accordingly for the removal position. An automatic adjustment run is often sufficient to adjust the image processing system used. During the adjustment run of the system, comparative photos are taken and saved in a room cube around a feature. From the comparison photos, the processing unit calculates, for example, the center of gravity of the feature and saves it in a table. When a workpiece is removed, the handling moves to the image recording position. The processing unit then compares the calculated focus of the feature from the recorded correction image with the stored focus values ​​of the comparison photos. On the basis of the relative position differences of the focal point of the feature, the processing unit calculates the correction values ​​for the axes X, Y, Z and the rotation around these axes. The industrial robot can take a correct removal position with these transmitted correction values.

See also