Share Email Print

Proceedings Paper

Automatic distribution of vision-tasks on computing clusters
Author(s): Thomas Müller; Binh An Tran; Alois Knoll
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper a consistent and efficient but yet convenient system for parallel computer vision, and in fact also realtime actuator control is proposed. The system implements the multi-agent paradigm and a blackboard information storage. This, in combination with a generic interface for hardware abstraction and integration of external software components, is setup on basis of the message passing interface (MPI). The system allows for data- and task-parallel processing, and supports both synchronous communication, as data exchange can be triggered by events, and asynchronous communication, as data can be polled, strategies. Also, by duplication of processing units (agents) redundant processing is possible to achieve greater robustness. As the system automatically distributes the task units to available resources, and a monitoring concept allows for combination of tasks and their composition to complex processes, it is easy to develop efficient parallel vision / robotics applications quickly. Multiple vision based applications have already been implemented, including academic, research related fields and prototypes for industrial automation. For the scientific community the system has been recently launched open-source.

Paper Details

Date Published: 25 January 2011
PDF: 10 pages
Proc. SPIE 7872, Parallel Processing for Imaging Applications, 787203 (25 January 2011); doi: 10.1117/12.872131
Show Author Affiliations
Thomas Müller, Technische Univ. München (Germany)
Binh An Tran, Technische Univ. München (Germany)
Alois Knoll, Technische Univ. München (Germany)

Published in SPIE Proceedings Vol. 7872:
Parallel Processing for Imaging Applications
John D. Owens; I-Jong Lin; Yu-Jin Zhang; Giordano B. Beretta, Editor(s)

© SPIE. Terms of Use
Back to Top