More and more image sensors are used in intelligent transportation systems. In practice, occlusion is always a problem when counting vehicles in congested traffic. This paper tries to present an approach to solve the problem. The proposed approach consists of three main procedures. Firstly, a new algorithm of background subtraction is performed. The aim is to segment moving objects from an illumination-variant background. Secondly, object tracking is performed, where the CONDENSATION algorithm is used. This can avoid the problem of matching vehicles in successive frames. Thirdly, an inspecting procedure is executed to count the vehicles. When a bus firstly occludes a car and then the bus moves away a few frames later, the car will appear in the scene. The inspecting procedure should find the "new" car and add it as a tracking object.
Approach for counting vehicles in congested traffic flow
Real-Time Imaging IX ; 2005 ; San Jose,California,United States
Proc. SPIE ; 5671
2005-02-25
Conference paper
Electronic Resource
English
Tracking vehicles in congested traffic
SPIE | 1997
|Tracking Vehicles in Congested Traffic
British Library Conference Proceedings | 1996
|Congested Traffic Flow: Observations and Theory
British Library Conference Proceedings | 1999
|Congested Traffic Flow: Observations and Theory
Transportation Research Record | 1999
|Congested Traffic Flow: Observations and Theory
Online Contents | 1999
|