Navigation : EXPO21XX > QUALITY & TESTING 21XX > H02: Shape and Form Analysis > Adaptive Vision
  • Offer Profile
  • Our engineers have been concentrating on creating computer vision software designed for specific applications for the last 11 years. Experience gained in projects related to intelligent video surveillance as well as biometric and medical systems helped the team to develop all the skills necessary to respond with solutions dedicated to different branches of computer vision.
Product Portfolio
  • Adaptive Vision Studio 2.4

  • Adaptive Vision Studio 2.4 is an easy to use development environment for creating machine vision applications. It solves real-life tasks in many different industries and gives you freedom in the selection of hardware, including smart cameras from several manufacturers.

    It is the best machine vision software that is simultaneously:
    • Intuitive - drag & drop development of algorithms and graphical user interfaces; instant insight into all intermediate results; clean design;
    • Powerful - loops, conditions, macrofilters and a comprehensive library of filters that are one of the fastest in the world;
    • Adaptable - support for hardware from many different vendors; C++ user filters; integrated with OpenCV.
      • Adaptive Vision Studio 2.4

      • How does it work?
        The application comes with a library of over 700 built-in computer vision filters. Users create programs by connecting filters with each other in an appropriate way. Various types of connections assure that any structure of data flow can be achieved, whereas hierarchical macrofilters allow for effective management of large-scale programs.

        Who is it for?
        Adaptive Vision Studio is designed to fit the needs of a wide community of machine vision engineers and researchers. People new to computer vision benefit from swift learning through interactive experimentation, whereas machine vision experts can do their job faster and in a more convenient way due to the lack of low-level programming hassle. Also C/C++ programmers with their own vision-related code bases can take advantage of the high interactiveness of Adaptive Vision Studio through easily integrated user filters.
  • Features

    • You Can See Everything

    • All programming is done by choosing filters and connecting them with each other. You can focus all your brain power on computer vision. For a quick demo see Your First Program video tutorial.

      The application is optimized for the needs of computer vision professionals. All intermediate results can be viewed and analysed providing you a full insight into algorithm performance.

    • Macrofilters

    • Without writing a single line of code, you can create arbitrarily complex algorithms. Loops and conditions are created implicitly with appropriate data connections. Go to Data Flow Programming for more information.

      Large programs can be organized into small, easy to understand portions - macrofilters. A macrofilter is a reusable sequence of filters with its own inputs, outputs and a data processing cycle.

    • Hardware Acceleration

    • There are hundreds of ready-to-use machine vision filters. They are organized into a well-defined category structure and comply to clear and consistent naming conventions. They are documented in the Filter Reference.

      Filters are aggressively optimized for the SSE technology and for multicore processors. Our implementations are one of the fastest in the world (as can be seen in the Performance section).

    • Any-shape ROIs

    • You can process not only images, but also regions, paths, geometrical primitives, profiles, histograms and more. For more details see this video.

      Image processing operations can be performed on entire images or within regions of arbitrary shape. Small and precise ROIs can be used to significantly speed up processing.

    • OpenCV Support

    • You can use user filters to integrate your own C/C++ code with the benefits of visual programming. It takes 30 seconds to build first user filter and 5 seconds to update one after recompilation. This video shows how easy and straightforward it is.

      Free, open-source filters from the OpenCV library are included. Together with a group of standard filters they can be used to create extremely cost-effective solutions for simple applications.

    • GigE Vision Support

    • Cameras from many different manufacturers are supported including Basler, PointGrey and XIMEA.

      Adaptive Vision Studio and Adaptive Vision GigE SDK are GigE Vision compliant products supporting everything that is needed - from camera configuration to high performance image acquisition. See this video presentation.

    • Executor Library

    • Programs created in Adaptive Vision Studio can be deployed with a lightweight runtime application. A user interface (HMI) can be defined with a simple XML file (available since 2.2).

      The runtime engine is also available as a DLL library that can be used in C, C++ or C# applications.

    • HMI Designer

    • You can easily create a custom graphical user interface and thus build the entire machine vision solution using a single software package.
  • Adaptive Vision Library

  • Adaptive Vision Library is a general purpose machine vision toolset optimised for the needs of industrial quality inspection. The main strengths of the library include the excellent performance and comprehensive set of machine vision algorithms with particularly good support of the low level techniques: image processing, blob analysis and contour analysis.
      • Adaptive Vision Library

      • The main part of the library is divided in six parts, defined according to the datatype(s) of interest:
        • Image Processing - containing methods for initial image preprocessing/refinement
        • Blob Analysis, Contour Analysis - two big toolsets for image analysis built upon the processing of regions (Blob Analysis) and subpixel-precise paths (Contour Analysis) extracted from an image
        • Profiles, Histograms - auxiliary toolsets for the processing and analysis od 1D data
        • Geometry 2D - platform for performing final measurements between objects found using (possibly) different tools.

        Additionally, the library provides support for a number of specialised techniques like 1D Measurement, Fourier Analysis and Shape-based Template Matching.

  • Relation between Adaptive Vision Library and Adaptive Vision Studio

  • Each function of the Adaptive Vision Library is a basis for corresponding filter available in Adaptive Vision Studio. Therefore it is possible (and advisable) to use the Adaptive Vision Studio as a convenient, point & click prototyping tool, even if one intends to develop the final solution in C++ using the Adaptive Vision Library.
    • Blob Analysis

    • High performance, any-shape ROI operations for unary and binary arithmetics, image refinement, morphology, smoothing, spatial transformations, feature extraction, gradient extraction, numerous thresholding methods, disc IO and more.

      Powerful set of robust operations for classic technique of blob analysis. Provides numerous methods of blob extraction, set arithmetics, region refinement, any-kernel morphology, skeletonization, spatial transformations, feature extraction, measurements and more.

    • Geometry 2D

    • Subpixel-precise toolset designed as an alternative to blob analysis, particularily suitable for shape analysis. Provides methods for contour extraction, refinement, segmentation, smoothing, classification, global transformations, feature extraction and more.

      Exhaustive toolset of geometric operations compatible with other parts of the library. Provides more than 50 operations for 2D geometry, including fitting of geometric primitives, measurements, intersections, tangents, feature extraction and more.

    • 1D Measurement

    • Auxillary toolsets allowing to refine and analyse 1D data extracted from the image. Innovative design of the Library puts the classic histograms and profiles far beyond their usual applications. It is not uncommon in Adaptive Vision Library to analyse the profile of distance between two paths, or histogram of the numeric features extracted from a set of objects.

      Set of methods for classic technique of extracting edges across image profile. The Library provides specialised methods for measuring paired edges of alternating characteristics and support measurements along any path.

    • Fourier Analysis

    • Efficient, robust and easy to use methods for template matching. Whenever low-level techniques are not enough to locate the object you look for, these tools provide sound alternative.

      Suitable both for educational experimentation and industrial application, this toolset provides methods for Fourier transform and image processing in the frequency domain.

    • Portability

    • In the Adaptive Vision Library careful design of algorithms goes hand in hand with exhaustive hardware optimisations, resulting in performance that puts the library among the fastests in the world. Our implementations make use of SSE instructions and parallel computations on multicore processors.

      The library does not use the STL, instead being based on simple and efficient Adaptive Template Library. The latter delivers most of the STL functionality whilst avoiding the iterator abstraction and advanced template techniques. Therefore the Adaptive Vision Library can be easily ported to various embedded platforms, including ones without the full support of the C++ templates.

    • Consistency

    • All datatypes features automatic memory management. Errors are handled explicitly by throwing an appropriate exception. Innovative optional inputs construction is provided for elegant handling of special values on inputs.

      Function names have a form of VERB + NOUN (e.g. SmoothImage, RotateVector). If there are several variants of a single operation they are distinguished with a suffix starting with an underscore (e.g. SmoothImage_Mean, SmoothImage_Gauss). All results are returned via reference output parameters, so that many outputs are always possible.

  • Example results