DocumentCode
2094870
Title
Real-time synchronized vision sensors over Ethernet
Author
Schuurman, Derek C. ; Capson, David W.
Author_Institution
Redeemer Univ. Coll., Ancaster, Ont., Canada
fYear
2004
fDate
16-18 Nov. 2004
Firstpage
136
Lastpage
143
Abstract
A network of real-time vision sensors is described using 100baseT Ethernet. Each vision sensor comprises a camera connected to a dedicated computer to form a "vision node". Each vision node is capable of capturing and processing images and communicating the results over the network to a master computer in real-time. Deterministic and timely operation using standard Ethernet is accomplished using three basic techniques: suppressing superfluous packets; using the UDP transport protocol; and using an application layer protocol based on master/slave round-robin polling. Deterministic communications also enable the acquisition times of the cameras to be synchronized over the Ethernet network. By synchronizing the vision nodes to interleave their capture times, network contention is avoided and the effective video sample rate is increased. An analysis is also performed to determine the maximum number of vision nodes that can be supported using this technique over 100baseT Ethernet.
Keywords
computer vision; distributed sensors; image sampling; image sensors; local area networks; telecommunication congestion control; transport protocols; 100baseT Ethernet; UDP transport protocol; application layer protocol; camera; dedicated computer; deterministic communications; effective video sample rate; image capture; image processing; master/slave round-robin polling; network contention; real-time vision sensors; sensor network; superfluous packet suppression; vision node; Bandwidth; Computer networks; Computer vision; Ethernet networks; Feedback; Intelligent sensors; Sensor phenomena and characterization; Smart cameras; Temperature sensors; Transport protocols;
fLanguage
English
Publisher
ieee
Conference_Titel
Local Computer Networks, 2004. 29th Annual IEEE International Conference on
ISSN
0742-1303
Print_ISBN
0-7695-2260-2
Type
conf
DOI
10.1109/LCN.2004.103
Filename
1367211
Link To Document