COUNTING PEOPLE GETTING IN AND OUT OF A BUS BY REAL-TIME IMAGE-SEQUENCE PROCESSING

The number of people getting in and out of a bus is an important param eter to allocate the proper number of buses for each connection-line o f a public transport service. On the other hand, the correct distribut ion of the available buses over the different paths, is fundamental to obtain an optimization of the whole transport network, and to reduce costs. In this paper, an automatic system using dynamic image sequence processing to count people getting in and out of a bus is presented. Some fast algorithms are used to detect motion, estimate its direction , and validate the presence of moving people. The system can deal with vibrations, lighting fluctuations and environmental variations. The m ain advantages are the execution speed and the reliability of the coun ting process, is performed correctly even if people flow in a chaotic and very clustered way.