About the Site Email Newsletter Links to Cycling Organisations
Bicycle and Public Transport Bicycle Network Planning Bicycle Strategies & Plans Bike Share Programs Cycling Data End of Trip Facilities Facility Design / Engineering Land Use Planning Mobility Management
Cycling Skills: Information for Riders Cycling Skills: Programs and Resources Organisations Professional Development Research
Awards and Recognition Behaviour Change Programs Economic Benefits of Cycling Environmental Benefits of Cycling Health Benefits of Cycling Maps Marketing Ride to School Ride to Shops Ride to Work Social Benefits of Cycling Women in Cycling
Bicycle Regulations Overviews Solutions Statistics & Common Crashes
Cycle Tourism: Promotion Cycle Tourism: Strategies Organisations Recreation: BMX Facilities Recreation: Off Road Facilities and Trails Recreation: Publications and Resources Recreation: Strategies Recreation: Trail and Facility Design Research
International Local Government National Government State & Territory Government
Cycling Innovations Encouragement & Promotion Enforcement & Road Safety Engineering & Planning Funding

Search

Font Decrease Font Normal Font Increase Print

Heikkilä, J. and Silvén, O. (2003), "A real-time system for monitoring of cyclists and pedestrians", University of Oulu, Finland. Research paper available for purchase from Science Direct

Heikkilä, J. and Silvén, O. (2003), "A real-time system for monitoring of cyclists and pedestrians", University of Oulu, Finland. Research paper available for purchase from Science Direct
Visit Site

Camera based systems are routinely used for monitoring highway traffic, supplementing inductive loops and microwave sensors employed for counting purposes. These techniques achieve very good counting accuracy and are capable of discriminating trucks and cars. However, pedestrians and cyclists are mostly counted manually. In this paper, we describe a new camera based automatic system that utilizes Kalman filtering in tracking and Learning Vector Quantization for classifying the observations to pedestrians and cyclists. Both the requirements for such systems and the algorithms used are described. The tests performed show that the system achieves around 80–90% accuracy in counting and classification.