Optimising Concrete Crack Detection: A Study of Transfer Learning with Application on Nvidia Jetson Nano
Open Access
Abstract
The use of Artificial Intelligence (AI) to detect defects such as concrete cracks in civil and transport infrastructure has the potential to make inspections less expensive, quicker, safer and more objective by reducing the need for on-site human labour. One deployment scenario involves using a drone to carry an embedded device and camera, with the device making localised predictions at the edge about the existence of defects using a trained convolutional neural network (CNN) for image classification. In this paper, we trained six CNNs, namely Resnet18, Resnet50, GoogLeNet, MobileNetV2, MobileNetV3-Small and MobileNetV3-Large, using transfer learning technology to classify images of concrete structures as containing a crack or not. To enhance the model’s robustness, the original dataset, comprising 3000 images of concrete structures, was augmented using salt and pepper noise, as well as motion blur, separately. The results show that Resnet50 generally provides the highest validation accuracy (96% with the original dataset and a batch size of 16) and the highest validation F1-score (95% with the original dataset and a batch size of 16). The trained model was then deployed on an Nvidia Jetson Nano device for real-time inference, demonstrating its capability to accurately detect cracks in both laboratory and field settings. This study highlights the potential of using transfer learning on Edge AI devices for Structural Health Monitoring, providing a cost-effective and efficient solution for automated crack detection in concrete structures.Keywords
Funding Information
- UniSQ International (AQIRF101-2022RD5)
- Advance Queensland Industry Research Fellowship (AQIRF101-2022RD5)
This publication has 25 references indexed in Scilit:
- Threshold-Based BRISQUE-Assisted Deep Learning for Enhancing Crack Detection in Concrete StructuresJournal of Imaging, 2023
- Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural networkComputers and Electronics in Agriculture, 2021
- A Critical Review on Structural Health Monitoring: Definitions, Methods, and PerspectivesArchives of Computational Methods in Engineering, 2021
- A large-scale sensor missing data imputation framework for dams using deep learning and transfer learning strategyMeasurement, 2021
- Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learningAutomation in Construction, 2021
- A scoping review of non-destructive testing (NDT) techniques in building performance diagnostic inspectionsConstruction and Building Materials, 2020
- Machine Learning Algorithms in Civil Structural Health Monitoring: A Systematic ReviewArchives of Computational Methods in Engineering, 2020
- Industry 4.0: Industrial Internet of Things (IIOT)2020
- Development of a LeNet-5 Gas Identification CNN Structure for Electronic NosesSensors, 2019
- Vibration-based structural health monitoring of offshore pipelines: numerical and experimental studyStructural Control and Health Monitoring, 2012