A computer vision approach for detection and counting of motorcycle riders in university campus

Essential tasks of automatic traffic monitoring are a vehicle classification and a vehicle or passenger counting system. These tasks provide useful data in planning transportation system. This paper presents an automatic system to classify a motorcycle and count riders on it. The system extracts moving objects and classifies them as a motorcycle or other moving objects based on features derived from their region properties using K-Nearest Neighbor (KNN) classifier. The heads of the riders on the recognized motorcycle are then counted based on projection profiling. Experiment results show an average correct motorcycle classification at 95.31% and correct rider count at 83.82%.