Design of Simple Vehicle Counter using Sidewalk Microphones

Vehicle counting is one of the fundamental tasks in the intelligent transportation system (ITS). Although automatic vehicle counters have been proposed to retrieve realtime traffic data, current automatic vehicle counters are suffered from high deployment costs, resulting in limited number of deployments. In this paper, we present a vehicle counter using sidewalk microphones that are easily deployed at a low cost. Our vehicle counter only relies on two microphones and counts vehicles using a sound map, which is a time-difference map of vehicle sound on the two microphones. We developed a vehicle count algorithm using a sound map. To minimize the effect of practical issues on vehicle counting, we also developed a simple image processing technique. We herein describe the design and implementation of our vehicle count system. Experimental evaluations reveal that our vehicle count system successfully counted vehicles with an F-measure of 0.92.

[1]  Sergio A. Velastin,et al.  Vehicle localisation and classification in urban CCTV streams , 2009 .

[2]  W. Jatmiko,et al.  ITS information source: Vehicle speed measurement using camera as sensor , 2012, 2012 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[3]  B. Bridge,et al.  Automatic traffic monitoring by intelligent sound detection , 1999 .

[4]  James F. Forren,et al.  Traffic monitoring by tire noise , 1999 .

[5]  Shiping Chen,et al.  Traffic monitoring using digital sound field mapping , 2001, IEEE Trans. Veh. Technol..

[6]  G. Carter,et al.  The generalized correlation method for estimation of time delay , 1976 .

[7]  P. Khosla,et al.  Vehicle sound signature recognition by frequency vector principal component analysis , 1998, IMTC/98 Conference Proceedings. IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No.98CH36222).