topic_bildverarbeitung_b

Image Capturing and Processing

Industrial machine vision is in constant need to further increase performance levels while also opening up new technologies to the mainstream. At the some time, there is an increasing demand for industrial real-time capabilities in order to execute vision processes within a set minimal timeframe.

The »RealTime Suite« by Kithara Software adresses these key issues and enables the development of cost-efficient as well as performance-efficient machine vision solutions for industrial fields such as automated quality assurance, robotics, autonomous cars or medical technology. This includes image capture, image processing as well as subsequent control reactions all in the same real-time context.

GigE Vision Kamera For industrial machine vision two camera standards have proven to be particularly trendsetting and future-proof— GigE Vision® und USB3 Vision. Both standards feature a similar set of benefits that make them highly suitable for a vast range of industrial fields and applications. Besides high data rates, both interfaces can also be optimally used for almost any task due to inexpensive and interchangeable standard hardware. Both interfaces can be configured with GenICam 2.0 which allows for the utilization of default functions as well as access to manufacturer-specific features.

Task and solution

In image processing the use of Windows OS is essential, because the most application programs require Windows. However, developers usually (without the use of real-time extensions) are confronted with avoidable problems:

  • individual data packets of GigE Vision cameras are not transferred, therefore, images are corrupted or only partial transferred,
  • The reaction time is delayed by the Windows application and is therefore, too long and not deterministic:

A case study for processes, which require the Camera Module of the »RealTime Suite« is the quality assurance of packaging industry. During this process the assessment whether a product meets the specification or not has to take place in a very short time in order to remove the blemished product from production process in time. The Camera Module of the »RealTime Suite« solves this problem impressively.

To avoid the loss of data packets the Camera Module provides large-sized memory buffer and real-time network drivers. The reaction of received GigE Vision images immediately takes place in a real-time context within a few microseconds. In order to trigger an immediate control reaction, it is possible to activate a real-time task.

With regard to the processing of especially large data package sizes, that resulted from high-resolution images with high frame rates ordinary Windows mechanisms can not handle this.

Camera Module

Image acquisition with GigE Vision® cameras in real-time

  • Common
  • Features

The Camera Module serves as a functional module for capturing image data of industrial cameras according to the GigE Vision® standard in real-time. It provides all necessary functions for detection and management and for creating real-time streams.

Large buffer memory along with real-time network drivers reliably prevent any loss of data packets. The reaction on incoming GigE Vision images takes place instantly in the context of the real-time environment within a few microseconds. In that moment a real-time task can be activated, in order to execute a control reaction instantly. The comprehensive image processing library HALCON of the Munich-based company MVTec GmbH can be also used in real-time, so you can implement powerful solutions.

The Camera Module delivers a data throughput of up to 125 MByte/s due to the real-time based network drivers, that means up to the theoretical maximum.

The results of the image processing can be given to the process even in the real-time context without any delay, e.g. over EtherCAT® or CANopen®. Accordingly, automation solutions can be easily combined with several other themes within the »RealTime Suite«.

The Camera Module needs the Packet Module as a requirement, which is providing the network drivers.

  • Image acquisition with GigE Vision® cameras in real-time, event or request based
  • multiple simultaneous cameras, hot-plugging, error processing, configuration in accordance with GenICam 2.0

General features

  • every GigE Vision® compliant camera is supported
  • connect to multiple cameras
  • hot plugging

Control

  • automatic connection handling
  • full access to camera configuration space
  • read and write camera memory
  • set custom heartbeat timeout
  • start and stop acquistion of images by software
  • set acquisition mode by software
  • GenICam xml configuration file automatically downloaded
  • access to GenICam features to configure your camera
  • error handling

Streams

  • one or more streams per camera possible
  • acquisition of images in real-time
  • high performance acquisition, no unnecessary copying
  • set your own buffer size and buffer count
  • get informed on missed or incomplete images

GenICam features

  • enumerate all categories
  • set and retrieve all accessible camera features like image format, pixel format, frame rate, exposure time and more

Image Processing

  • write your own machine vision application using libraries like HALCON
  • image processing libraries are loaded to kernel mode using the //Kernel Module//
  • processing is done in real-time
  • do operations like: matching, segmentation, 3D matching, OCR and more

Vision Module

Image processing with Vision in real-time

  • Common
  • Features

The Vision Module complements the RealTime Module and supports industrial cameras compliant with the GigE Vision® standard and thus enables an immediate control reaction when the image has been captured and received by the PC. The widely used image processing library HALCON of MVTec from Munich/Germany is suitable for further processing of image data in real-time*, so that the implementation of powerful solutions is possible. Alternatively, the open library OpenCV can also be used.

*The license must be ordered separately from the company MVTec

  • Real-time image processing – write your own machine vision application using libraries like HALCON™ or OpenCV
  • HALCON or OpenCV image processing library is loaded into real-time context
  • Image processing is done in real-time tasks
  • Automatic parallelization
  • Do operations like: matching, segmentation, 3D matching, OCR, and more
  • After processing, instantly initiate control reaction, e.g. via EtherCAT® Master, CANopen® Master or PLC