Traffic count is fundamental for monitoring traffic flows on a transportation network and for the solution of different problems (as, for example, the estimation of the Origin/Destination demand matrix). Different techniques and instruments, each one with specific advantages and disadvantages, can be used for counting the vehicles on a transportation network. In this paper the use of a passive acoustic detector together with two neural networks working sequentially is proposed for counting the cars on the urban roads. The results obtained with this system are satisfactory and comparable with the existing ones. The proposed system also shows a large improvement of the cost/benefit ratio.
An Acoustic Passive Detector for Traffic Counts with Neural Networks / Calabro´, A; Postorino, M; Sarne', G. - (2002), pp. 215-220. ( NEURAL NETS WIRN VIETRI-01 (WIRN ’01), SALERNO, ITALY 17-19/05/2001) [doi: 10.1007/978-1-4471-0219-9_23].
An Acoustic Passive Detector for Traffic Counts with Neural Networks
POSTORINO M;SARNE' G
2002-01-01
Abstract
Traffic count is fundamental for monitoring traffic flows on a transportation network and for the solution of different problems (as, for example, the estimation of the Origin/Destination demand matrix). Different techniques and instruments, each one with specific advantages and disadvantages, can be used for counting the vehicles on a transportation network. In this paper the use of a passive acoustic detector together with two neural networks working sequentially is proposed for counting the cars on the urban roads. The results obtained with this system are satisfactory and comparable with the existing ones. The proposed system also shows a large improvement of the cost/benefit ratio.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
