A Novel Real-Time Autonomous Crack Inspection System Based on Unmanned Aerial Vehicles

Abstract

Traditional methods on crack inspection for large infrastructures require a number of structural health inspection devices and instruments. They usually use the signal changes caused by physical deformations from cracks to detect the cracks, which is time-consuming and cost-ineffective. In this work, we propose a novel real-time crack inspection system based on unmanned aerial vehicles for real-world applications. The proposed system successfully detects and classifies various types of cracks. It can accurately find the crack positions in the world coordinate system. Our detector is based on an improved YOLOv4 with an attention module, which produces 90.02% mean average precision (mAP) and outperforms the YOLOv4-original by 5.23% in terms of mAP. The proposed system is low-cost and lightweight. Moreover, it is not restricted by navigation trajectories. The experimental results demonstrate the robustness and effectiveness of our system in real-world crack inspection tasks.

Reinforced concrete surface cracks length detection and length estimation by using digital image processing approach

“…Even though the visual inspection by inspector's naked eye, for monitoring the damages state, i.e., measuring the crack length, on RC structures have worked in the past, they suffer certain limitations. These methods involved manual and non-systematic data collection [8], need expert judgement [9], and are prone to human error [10], making them appear to be a time-consuming and expensive task [11]. The utilization of automated digital procedures for crack detection and crack length analysis is deemed as another option which is vital in replacing the visual inspection approach.…”

Threshold-Based BRISQUE-Assisted Deep Learning for Enhancing Crack Detection in Concrete Structures

“…For major civil and construction assets, semi-autonomous or remote inspections are sometimes carried out with Unmanned Aerial Vehicles (UAVs) or wholesale robotic platforms fit with inspection equipment, as reviewed in [19]. State-of-the-art research showcases the ability to capture cracked surfaces using moving vehicles [20] or with UAVs [21]. In the majority of the reported literature, the process of capturing images is typically conducted separately from the crack detection phase.…”