Open Access

ARTICLE

Convolutional Neural Network for Overcrowded Public Transportation Pickup Truck Detection

Jakkrit Suttanuruk¹, Sajjakaj Jomnonkwao^1,*, Vatanavong Ratanavaraha¹, Sarunya Kanjanawattana²

1 School of Transportation Engineering, Institute of Engineering, Suranaree University of Technology, Nakhon Ratchasima, 30000, Thailand
2 School of Computer Engineering, Institute of Engineering, Suranaree University of Technology, Nakhon Ratchasima, 30000, Thailand

* Corresponding Author: Sajjakaj Jomnonkwao. Email:

Computers, Materials & Continua 2023, 74(3), 5573-5588. https://doi.org/10.32604/cmc.2023.033900

Received 30 June 2022; Accepted 03 October 2022; Issue published 28 December 2022

Abstract

Thailand has been on the World Health Organization (WHO)’s notorious deadliest road list for several years, currently ranking eighth on the list. Among all types of road fatalities, pickup trucks converted into vehicles for public transportation are found to be the most problematic due to their high occupancy and minimal passenger safety measures, such as safety belts. Passenger overloading is illegal, but it is often overlooked. The country often uses police checkpoints to enforce traffic laws. However, there are few or no highway patrols to apprehend offending drivers. Therefore, in this study, we propose the use of existing closed-circuit television (CCTV) traffic cameras with deep learning techniques to classify overloaded public transport pickup trucks (PTPT) to help reduce accidents. As the said type of vehicle and its passenger occupancy characteristics are unique, a new model is deemed necessary. The contributions of this study are as follows: First, we used various state-of-the-art object detection YOLOv5 (You Only Look Once) models to obtain the optimum overcrowded model pretrained on our manually labeled dataset. Second, we made our custom dataset available. Upon investigation, we compared all the latest YOLOv5 models and discovered that the YOLOv5L yielded the optimal performance with a mean average precision (mAP) of 95.1% and an inference time of 33 frames per second (FPS) on a graphic processing unit (GPU). We aim to deploy the selected model on traffic control computers to alert the police of such passenger-overloading violations. The use of a chosen algorithm is feasible and is expected to help reduce traffic-related fatalities.

---

Keywords

---