Title: Enhanced packet loss recovery for real time PC-based GigE vision AVI systems

Authors: Khaled Taouil; Tarek Jellad; Zied Chtourou

Addresses: Machine Control and Power Grid Unit, The National School of Engineers of Sfax, University of Sfax, Route de soukra 3038, Tunisia ' Machine Control and Power Grid Unit, The National School of Engineers of Sfax, University of Sfax, Route de soukra 3038, Tunisia ' Machine Control and Power Grid Unit, The National School of Engineers of Sfax, University of Sfax, Route de soukra 3038, Tunisia

Abstract: GigE vision could be a viable solution for seamless and cost effective integration of machine vision in manufacturing processes. Transmission delays, inherent to streaming and lost packets protocol implemented within the GigE, often jeopardise the implementation of networked PC-based machine vision. This is related to GigE vision open standard handling data integrity and error control through control and stream protocols (GVSP and GVCP) that implement data resend functions. In this work, we study the effect of data loss on the real time performance of distributed GigE vision AVI systems. We also introduce an optimised error recovery function based on definition of packets of interest (POIs) that allows for selective lost packet recovery based on their pertinence to subsequent machine vision processing. This scheme alleviates the traffic overhead by avoiding non-useful retransmissions. This mechanism allows reducing the latency and improving the predictability of such systems.

Keywords: automated visual inspection; packet of interest; POI; packet resend; GigE vision; machine vision; packet loss recovery; automated inspection; manufacturing industry; data integrity; error control; data resend; error recovery; traffic overhead; latency; predictability.

DOI: 10.1504/IJCNDS.2015.069677

International Journal of Communication Networks and Distributed Systems, 2015 Vol.14 No.4, pp.433 - 455

Received: 09 Jan 2014
Accepted: 07 Sep 2014
Published online: 29 May 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article