YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes

TL;DR

This paper evaluates YOLOv8's effectiveness in detecting road hazards like potholes, sewer covers, and manholes, comparing it with earlier versions and optimizing its performance for real-world applications.

Contribution

The study provides a comprehensive analysis of YOLOv8's architecture, optimization techniques, and performance in detecting diverse road hazards, advancing the application of deep learning in infrastructure safety.

Findings

YOLOv8 outperforms YOLOv5 and YOLOv7 in detection accuracy.

Image preprocessing and hyperparameter tuning significantly improve detection performance.

YOLOv8 demonstrates robust generalization across diverse road hazard scenarios.

Abstract

Effective detection of road hazards plays a pivotal role in road infrastructure maintenance and ensuring road safety. This research paper provides a comprehensive evaluation of YOLOv8, an object detection model, in the context of detecting road hazards such as potholes, Sewer Covers, and Man Holes. A comparative analysis with previous iterations, YOLOv5 and YOLOv7, is conducted, emphasizing the importance of computational efficiency in various applications. The paper delves into the architecture of YOLOv8 and explores image preprocessing techniques aimed at enhancing detection accuracy across diverse conditions, including variations in lighting, road types, hazard sizes, and types. Furthermore, hyperparameter tuning experiments are performed to optimize model performance through adjustments in learning rates, batch sizes, anchor box sizes, and augmentation strategies. Model evaluation is based on Mean Average Precision (mAP), a widely accepted metric for object detection performance. The research assesses the robustness and generalization capabilities of the models through mAP scores calculated across the diverse test scenarios, underlining the significance of YOLOv8 in road hazard detection and infrastructure maintenance.