Abstract
This study introduces a project aimed at the design and deployment of an intelligent passenger counting system for public transport. The objective is to enhance fare evasion control and reduce financial losses for transport operators through automated tracking of passenger entries and exits. The system employs the YOLO and DeepSORT algorithms, known for their high accuracy in identifying and monitoring passengers within complex environments. Experimental investigations reveal the critical role of camera type and positioning on system efficacy; notably, utilizing USB cameras over IP cameras enhances frame processing speed and overall system performance. However, testing has identified areas for improvement, particularly in managing group movements, minimizing frame loss, and increasing real-time accuracy. Future development efforts will focus on integrating depth sensors and crafting sophisticated data analysis algorithms to refine passenger counting precision during peak traffic periods. Anticipated outcomes of this project include optimized transport routes and schedules, improved management of passenger flows, heightened passenger satisfaction, and effective fare evasion prevention.