Automated Pedestrian Detection and Recognition Applied to Automatic Gate Machines in Urban Rail Transit

This paper presents a novel pedestrian detection and recognition method based on a new photoelectric sensor layout for increasing the recognition rate and the recognition speed of the Automatic Gate Machine (AGM). First of all, a new sensors layout is designed. Next, by collecting the time and sequence of pedestrian breaking the rays of the sensors, an algorithm of combining the time sequence analysis and event analysis is developed to detect and judgment the legality of the pedestrians so that the gate of the AGM is either opened or closed. Then, the algorithm is implemented by software method and FPGA method respectively. Finally, the experiments on the prototype of AGM prove that the recognition rate and the recognition speed are increased effectively.