Low-cost localization service for roadside sensors based on passive information

The remote surveillance and tracking of vehicles on roads is generally achieved by means of a network of sensors deployed along the roadside. The effectiveness of such networks depends fundamentally on the precision with which the sensor locations are known Global Positioning Systems provide an effe...

Full description

Saved in:
Bibliographic Details
Published in:Journal of high speed networks 2017-01, Vol.23 (4), p.323-339
Main Authors: Li, Jung-Shian, Kao, Chuan-Kai, Tsai, Chia-Yang, Liu, I-Hsien, Liu, Chuan-Gang
Format: Article
Language:English
Subjects:
Algorithms
Clustering
Computer simulation
Localization
Low cost
Remote sensors
Roads & highways
Satellite navigation systems
Sensors
System effectiveness
Traffic surveillance
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The remote surveillance and tracking of vehicles on roads is generally achieved by means of a network of sensors deployed along the roadside. The effectiveness of such networks depends fundamentally on the precision with which the sensor locations are known Global Positioning Systems provide an effective means of pinpointing the sensor locations. However, such systems are expensive, and are therefore impractical for large-scale sensor deployment. Accordingly, this paper proposes a low-cost sensor localization service based on binary detection information and a road map. In the proposed algorithm, the sensors are classified as either intersection nodes or non-intersection nodes in accordance with the stochastic characteristics of the binary detection information. Having identified all of the non-intersection nodes along each road segment, the intersection nodes are connected with the non-intersection nodes by means of a clustering technique. Finally, the positions of the roadside sensors are identified by mapping the clustered sensors to the known road map. The simulation results show that the proposed algorithm outperforms existing localization algorithms reported in the literature.
ISSN:0926-6801
1875-8940
DOI:10.3233/JHS-170574