Abstract | ||
---|---|---|
We present a customized system for vehicle tracking and classification.The system has been designed to work with real world data provided by the industry.The tracker is designed adapting the template matching approach to the data.The classifier uses machine learning to discriminate between cars and trucks.The system outperforms the state of the art on the considered data. We present a unified system for vehicle tracking and classification which has been developed with a data-driven approach on real-world data. The main purpose of the system is the tracking of the vehicles to understand lane changes, gates transits and other behaviors useful for traffic analysis. The discrimination of the vehicles into two classes (cars vs. trucks) is also required for electronic truck-tolling. Both tracking and classification are performed online by a system made up of two components (tracker and classifier) plus a controller which automatically adapts the configuration of the system to the observed conditions. Experiments show that the proposed system outperforms the state-of-the-art algorithms on the considered data. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1016/j.eswa.2015.05.055 | Expert Systems with Applications |
Keywords | Field | DocType |
Traffic monitoring,Vehicle tracking,Vehicle classification,Data-driven,Template matching | Template matching,Truck,Computer vision,Control theory,Traffic analysis,Data-driven,Computer science,Tracking system,Artificial intelligence,Classifier (linguistics),Vehicle tracking system | Journal |
Volume | Issue | ISSN |
42 | 21 | 0957-4174 |
Citations | PageRank | References |
15 | 0.74 | 19 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sebastiano Battiato | 1 | 659 | 78.73 |
Giovanni Maria Farinella | 2 | 412 | 57.13 |
Antonino Furnari | 3 | 85 | 18.86 |
Giovanni Puglisi | 4 | 383 | 31.62 |
Anique Snijders | 5 | 18 | 1.15 |
Jelmer Spiekstra | 6 | 18 | 1.15 |