A real-time system for monitoring of cyclists and pedestrians

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