Paper Contents
Abstract
: Structural health monitoring (SHM) plays a crucial role in ensuring the safety and durability of infrastructure, yet traditional inspection methods remain slow and prone to human error. With the growth of computer vision, object detection models such as YOLO (You Only Look Once) offer promising solutions for automating defect detection. This study presents a comparative evaluation of YOLOv5, YOLOv10n, YOLOv10s, and YOLOv10m for identifying cracks, spalling, and surface deterioration. Each version provides a different balance between accuracy, speed, and computational costranging from lightweight Nano models designed for faster deployment to larger Medium variants focused on precision. By testing these models under consistent conditions, the research highlights their strengths and limitations, aiming to guide the choice of suitable YOLO versions for reliable and efficient SHM applications.
Copyright
Copyright © 2025 Mitali chaudhary. This is an open access article distributed under the Creative Commons Attribution License.
