Optimizing Helmet Detection with Hybrid YOLO Pipelines: A Detailed Analysis

TL;DR

This paper evaluates recent YOLO models for helmet detection, introduces a hybrid YOLO pipeline that outperforms individual models, and analyzes their reliability and computational efficiency for real-time applications.

Contribution

It proposes a novel hybrid YOLO architecture that significantly improves helmet detection performance over standard YOLO models.

Findings

h-YOLO outperforms individual YOLO models in accuracy

The hybrid model reduces training and testing times

h-YOLO demonstrates higher recall, precision, and mAP

Abstract

Helmet detection is crucial for advancing protection levels in public road traffic dynamics. This problem statement translates to an object detection task. Therefore, this paper compares recent You Only Look Once (YOLO) models in the context of helmet detection in terms of reliability and computational load. Specifically, YOLOv8, YOLOv9, and the newly released YOLOv11 have been used. Besides, a modified architectural pipeline that remarkably improves the overall performance has been proposed in this manuscript. This hybridized YOLO model (h-YOLO) has been pitted against the independent models for analysis that proves h-YOLO is preferable for helmet detection over plain YOLO models. The models were tested using a range of standard object detection benchmarks such as recall, precision, and mAP (Mean Average Precision). In addition, training and testing times were recorded to provide the overall scope of the models in a real-time detection scenario.