Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 323-339 |
Number of pages | 17 |
Journal | Journal of High Speed Networks |
Volume | 23 |
Issue number | 4 |
DOIs | |
Publication status | Published - 2017 Jan 1 |
All Science Journal Classification (ASJC) codes
- Information Systems
- Hardware and Architecture
- Computer Networks and Communications