A study of the city bus passenger flow intelligent statistical algorithm based on motion vector tracking

Abstract

Bus passenger flow collection technology is a subject urgently to be solved in current city intelligent transport system construction. By using self-developed multi-sensor array devices to collect the foot type data of passengers getting on and off, a kind of bus passenger flow intelligent recognition and statistical algorithms based on motion vector tracking is researched and proposed. The basic idea is based on establishing the motion vector model, determining the optimal solution of motion vector by advance prediction method, similarity criterion and dynamic search strategy according to the law of human body kinematics, tracking the motion process of passengers dynamically, ultimately, determining the movement direction of the passengers. The actual test results show that this algorithm can accurately and effectively deal with all kinds of complicated conditions.