Performance Analysis of YOLO-based Architectures for Vehicle Detection from Traffic Images in Bangladesh

TL;DR

This paper evaluates different YOLO-based deep learning architectures for vehicle detection in traffic images from Bangladesh, identifying YOLOV5x as the most effective for real-time applications.

Contribution

It provides a comparative performance analysis of YOLOv3, YOLOv5s, and YOLOv5x on Bangladeshi traffic datasets, highlighting the best model for vehicle detection.

Findings

YOLOV5x outperforms YOLOv3 and YOLOv5s in mAP by 7% and 4%.

YOLOV5x achieves 12% higher accuracy than YOLOv3.

The study demonstrates the suitability of YOLOV5x for real-time vehicle detection in Bangladesh.

Abstract

The task of locating and classifying different types of vehicles has become a vital element in numerous applications of automation and intelligent systems ranging from traffic surveillance to vehicle identification and many more. In recent times, Deep Learning models have been dominating the field of vehicle detection. Yet, Bangladeshi vehicle detection has remained a relatively unexplored area. One of the main goals of vehicle detection is its real-time application, where `You Only Look Once' (YOLO) models have proven to be the most effective architecture. In this work, intending to find the best-suited YOLO architecture for fast and accurate vehicle detection from traffic images in Bangladesh, we have conducted a performance analysis of different variants of the YOLO-based architectures such as YOLOV3, YOLOV5s, and YOLOV5x. The models were trained on a dataset containing 7390 images belonging to 21 types of vehicles comprising samples from the DhakaAI dataset, the Poribohon-BD dataset, and our self-collected images. After thorough quantitative and qualitative analysis, we found the YOLOV5x variant to be the best-suited model, performing better than YOLOv3 and YOLOv5s models respectively by 7 & 4 percent in mAP, and 12 & 8.5 percent in terms of Accuracy.