Passenger-Luggage Combined Motion Model and Abnormal State Recognition in Public Transportation Hubs

In public transportation hubs, the combined motion (CM) between a passenger and his luggage is a primary movement form. The state of CM always influences the stability of the movement of passenger crowds. While there is still a lack of systematic studies on the passenger-luggage combined motion, even most state-of-the-art literatures focus only on the impact of luggage on the overall efficiency of crowd evacuation. To fill this academic lag, this study investigated the motion relationship between passengers and luggage and then proposed a passenger-luggage combined motion model (PLCMM), which helps determine the relevance between passengers and luggage. Furthermore, a novel energy-based criterion for the stability of PLCMM and an abnormal state recognition model were established. Finally, the proposed model and criteria were validated in the waiting hall of Shanghai Hongqiao High-speed Railway Station, as a typical large public transportation scenario. The luggage abnormality recognition model can identify three abnormal states, i.e., luggage falling off, tail dumping, and sudden acceleration. A performance comparison between the proposed PLCMM and five other representative models was conducted from the aspects of scenarios, algorithm complexity, and research focus. The detection accuracy of the PLCCM was 96.154% and the algorithm complexity was considerably lower than the complexity exhibited by the purely computer vision-based approaches. The results demonstrated that PLCMM aligned closely with the ground truth, and outperformed other state-of-the-art models. The stability criterion can be employed to assess the impact of lateral perturbation forces on the stability of the passenger-luggage combined motion, to support the daily passenger flow control and management in more public traffic areas.