YOLOv5-Based Object Detection for Emergency Response in Aerial Imagery

TL;DR

This paper develops a YOLOv5-based system for real-time detection of emergency vehicles and incidents in aerial imagery, addressing challenges like small object detection and complex backgrounds.

Contribution

It introduces a custom dataset and pipeline for training YOLOv5 on aerial emergency response imagery, demonstrating effective real-time detection capabilities.

Findings

YOLOv5 achieves high accuracy and speed in aerial emergency detection

The approach effectively detects small objects in complex backgrounds

The system is suitable for real-time emergency response applications

Abstract

This paper presents a robust approach for object detection in aerial imagery using the YOLOv5 model. We focus on identifying critical objects such as ambulances, car crashes, police vehicles, tow trucks, fire engines, overturned cars, and vehicles on fire. By leveraging a custom dataset, we outline the complete pipeline from data collection and annotation to model training and evaluation. Our results demonstrate that YOLOv5 effectively balances speed and accuracy, making it suitable for real-time emergency response applications. This work addresses key challenges in aerial imagery, including small object detection and complex backgrounds, and provides insights for future research in automated emergency response systems.