Paper Info
Title
Occlusion Robust Vehicle Tracking based on SOM (Self-Organizing Map)
Abstract
Traffic monitoring systems based on image and sequence analyses are widely employed in Intelligent Transportation Systems (ITS's) in order to analyze traffic parameters and statistics. To this purpose, tracking objects is often needed. However, occlusions can mislead a vehicle tracking system based on a single camera, thus resulting in tracking errors. In this work we present a vehicle tracking algorithm based on the KLT feature tracker which exploits a Kohonen Self Organizing Map (SOM) to drastically reduce tracking errors arising from occlusions, thus increasing the overall robustness of the system. Our method has been implemented in a real-time traffic monitoring system that has been working on daily urban traffic scenes. The experimental results we present assess the effectiveness of our approach even in the presence of quite congestioned traffic situations.
Year
DOI
Venue
2005
10.1109/ACVMOT.2005.87
WACV/MOTION
Keywords
Field
DocType
klt feature tracker,intelligent transportation systems,congestioned traffic situation,vehicle tracking system,occlusion robust vehicle tracking,traffic parameter,traffic monitoring system,daily urban traffic scene,kohonen self organizing map,self-organizing map,real-time traffic monitoring system,image analysis,robustness,vehicle tracking,statistical analysis
Computer vision,Monitoring system,Pattern recognition,Computer science,Tracking system,Self-organizing map,Exploit,Robustness (computer science),Condition monitoring,Artificial intelligence,Intelligent transportation system,Vehicle tracking system
Conference
ISBN
Citations 
PageRank 
0-7695-2271-8-2
5
0.77
References 
Authors
6
3
Name
Order
Citations
PageRank
Alessandro Bevilacqua120026.45
Luigi Di Stefano2173288.17
Stefano Vaccari3171.86