Abstract
Multiple object tracking (MOT), a key task in image recognition, poses a persistent challenge in balancing processing speed and tracking accuracy. This study presents a novel approach that leverages quantum annealing (QA) to expedite computation speed, while improving tracking accuracy through the ensemble processing of object tracking methods. A method to improve the matching integration process is also proposed. By utilizing the sequential nature of MOT, this study further augments the tracking method via reverse annealing. Experimental validation confirms the maintenance of high accuracy with an annealing time of a mere 3 μs per tracking process. Notably, the time-to-solution achieved reductions of over 99% compared to conventional QA implementations. The proposed method holds significant potential for real-time MOT applications, including traffic flow measurement for urban traffic light control, collision prediction for autonomous robots and vehicles, and management of products mass-produced in factories.