Skip to main content

Microprocessor Open Vision Environment

Objective

The objective of MOVE was to undertake a feasibility study of a vision environment that would be flexible, modular and open - it would enable integration of current and future (heterogeneous) processors, actuators, sensors and the necessary software and it would facilitate communications with the external world. This environment would be used in the design of a number of industrial vision applications that correspond to real industrial requirements
A specification of a microprocessor open vision environment has been drawn up and validated that contains the following desired technical characteristics: modularity; flexibility; openness; ease of use; cost effectiveness; scalability; high performance.

The MOVE environment is a 3 layered model consisting of:
a vision design environment within which a vision application may rapidly be prototyped and efficiently tested;
an implementation environment within which a target platform is specified and on to which the code is compiled. It is based on vertical block line (VBL) technology and the ANDR format;
a MOVE engine, within which it is possible to integrate heterogeneous processors in the specified environment and onto which the application code will actually run.

The originality of the framework developed is that within its vision can be used to address an arbitrarily wide range of applications, therefore becoming less dependent on the specifics of demonstrators. Moreover, this environment incorporates apart from the use of existing software and hardware vision modules, a wide range of emerging open microprocessor systems initiative (OMI) technologies including fast data communication pathways, software portability tools, flexible real time operating systems, advanced debugging facilities, new high performance computing elements, etc.
From the practical point of view the aim of the project was to propose a high performance vision system and a number of industrial Machine Vision application Demonstrators. The project was based on the fact that the major barrier to the commercial exploitation of complex machine vision systems is the lack of a general framework for integrating all the available software and hardware solutions into a complete vision environment rather than the lack of particular software or hardware solutions in themselves.

The approach was to

- identify technical requirements
- identify some classes of industrial vision applications where some software solutions exist but no hardware solution is economically viable
- identify and evaluate the existing hardware and software solutions which are well suited to the requirements
- develop a methodology to assemble existing software solutions to a coherent whole
- express the software requirements in terms of programming and debugging facilities to the OMI software system designers
- evaluate ways for integrating heterogeneous processors in the specified environment
- identify insufficient or missing hardware modules to the OMI hardware specialists.

Coordinator

ITMI
Address
11 Chemin Des Prés
38243 Meylan
France

Participants (4)

GEC Marconi Ltd
United Kingdom
Address
Elstree Way
WD6 1RX Borehamwood
Institut National Polytechnique de Grenoble
France
Address
46 Avenue Félix Viallet
38031 Grenoble
Institut National de Recherches en Informatique et en Automatique (INRIA)
France
Address
Sophia Antipolis
06561 Valbonne
University of Sheffield
United Kingdom
Address
Western Bank
S10 2TN Sheffield