Image Segmentation of Corrosion Damages in Industrial Inspections

In this paper we provide insights and methods for using image segmentation for the purposes of automatic corrosion damage detection. Automatic image analysis is needed in order to process all data retrieved from drone-driven industrial inspections. To this end we provide three main contributions. First, 608 images with corrosion damages are instance-wise annotated with binary segmentation masks to construct a dataset. Second, a novel, two-stage data augmentation scheme is developed and empirically shown to significantly reduce overfitting. Finally, Mask R-CNN and PSPNet are evaluated on the corrosion dataset using this and other data augmentation methods. With 77.5% and 73.2% mean intersection over union (mIoU) for Mask R-CNN and PSPNet, respectively, the results are very promising. It is concluded that image segmentation can aid automating industrial inspections of steel constructions in the future, and that instance segmentation is likely more useful than semantic segmentation due to its applications to a wider range of use-cases.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Aksel A. Transeth,et al.  Classification of corrosion and coating damages on bridge constructions from images using convolutional neural networks , 2020, International Conference on Machine Vision.

[5]  Gregg Podnar,et al.  Image understanding algorithms for remote visual inspection of aircraft surfaces , 1997, Electronic Imaging.

[6]  Hongwei Huang,et al.  Deep learning–based image instance segmentation for moisture marks of shield tunnel lining , 2020 .

[7]  Paul Scheunders,et al.  Classification of Corrosion Images by Wavelet Signatures and LVQ Networks , 1995, CAIP.

[8]  Bolei Zhou,et al.  Scene Parsing through ADE20K Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Osama Moselhi,et al.  Classification of Defects in Sewer Pipes Using Neural Networks , 2000 .

[13]  Oral Büyüköztürk,et al.  Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types , 2018, Comput. Aided Civ. Infrastructure Eng..

[14]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Luca Petricca,et al.  CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TECHNIQUES AND DEEP LEARNING MODEL , 2016 .

[17]  Sangwook Lee,et al.  Automated recognition of surface defects using digital color image processing , 2006 .

[18]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[19]  Cao Vu Dung,et al.  Autonomous concrete crack detection using deep fully convolutional neural network , 2019, Automation in Construction.

[20]  Mohammad R. Jahanshahi,et al.  Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection , 2018 .

[21]  Mel Siegel,et al.  Remote Enhanced Visual Inspection of Aircraft by a Mobile Robot , 1998 .