Evaluating the Performance of Video-Based Automated Passenger Counting Systems in Real-World Conditions: A Comparative Study

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 18; p. 7719
• Main Authors: Pronello, Cristina, Garzón Ruiz, Ximena Rocio
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023; MDPI
• Subjects: Accuracy; Algorithms; Artificial intelligence; automated passenger counting (APC); Automation; camera-based systems; Cameras; Comparative analysis; Deep learning; Kalman filters; Local transit; Manufacturers; Methods; Neural networks; optical systems; Passengers; public transport; Public transportation; Sensors; Surveillance; Vehicles; Australia
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23187719

Automatic passenger counting (APC) systems in public transport are useful in collecting information that can help improve the efficiency of transport networks. Focusing on video-based passenger counting, the aim of this study was to evaluate and compare an existing APC system, claimed by its manufacturer to be highly accurate (98%), with a newly developed low-cost APC system operating under the same real-world conditions. For this comparison, a low-cost APC system using a Raspberry Pi with a camera and a YOLOv5 object detection algorithm was developed, and an in-field experiment was performed in collaboration with the public transport companies operating in the cities of Turin and Asti in Italy. The experiment shows that the low-cost system was able to achieve an accuracy of 72.27% and 74.59%, respectively, for boarding and alighting, while the tested commercial APC system had an accuracy, respectively, of 53.11% and 55.29%. These findings suggest that current APC systems might not meet expectations under real-world conditions, while low-cost systems could potentially perform at the same level of accuracy or even better than very expensive commercial systems.