AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection
Open Access
- 7 November 2021
- journal article
- research article
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (7) , 8087-8098
Abstract
Corrosion has been concerned as a serious safety issue for metallic facilities. Visual inspection carried out by an engineer is expensive, subjective and time-consuming. Micro Aerial Vehicles (MAVs) equipped with detection algorithms have the potential to perform safer and much more efficient visual inspection tasks than engineers. Towards corrosion detection algorithms, convolution neural networks (CNNs) have enabled the power for high accuracy metallic corrosion detection. However, these detectors are restricted by MAVs on-board capabilities. In this study, based on You Only Look Once v3-tiny (Yolov3-tiny), an accurate deep learning-based metallic corrosion detector (AMCD) is proposed for MAVs on-board metallic corrosion detection. Specifically, a backbone with depthwise separable convolution (DSConv) layers is designed to realise efficient corrosion detection. The convolutional block attention module (CBAM), three-scale object detection and focal loss are incorporated to improve the detection accuracy. Moreover, the spatial pyramid pooling (SPP) module is improved to fuse local features for further improvement of detection accuracy. A field inspection image dataset labelled with four types of corrosions (the nubby corrosion, bar corrosion, exfoliation and fastener corrosion) is utilised for training and testing the AMCD. Test results show that the AMCD achieves 84.96% mean average precision (mAP), which outperforms other state-of-the-art detectors. Meanwhile, 20.18 frames per second (FPS) is achieved leveraging NVIDIA Jetson TX2, the most popular MAVs on-board computer, and the model size is only 6.1 MB.Keywords
Funding Information
- UK Oil and Gas Technology Centre (AI-P-028)
- China Scholar Council
- University of Strathclyde
This publication has 33 references indexed in Scilit:
- Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image ClassificationApplied Sciences, 2017
- Corrosion in onshore production and transmission sectors—current knowledge and challenges2017
- SSD: Single Shot MultiBox Detector2016
- Deep Residual Learning for Image Recognition2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Corrosion Detection for Automated Visual Inspection2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Performance Evaluation for Predictive Modeling2007
- An efficient k-means clustering algorithm: analysis and implementationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002