Estimation of Deterioration Levels of Transmission Towers via Deep Learning Maximizing Canonical Correlation Between Heterogeneous Features

This paper presents estimation of deterioration levels of transmission towers via deep learning maximizing the canonical correlation between heterogeneous features. In the proposed method, we newly construct a correlation-maximizing deep extreme learning machine (CMDELM) based on a local receptive field (LRF). For accurate deterioration level estimation, it is necessary to obtain semantic information that effectively represents deterioration levels. However, since the amount of training data for transmission towers is small, it is difficult to perform feature transformation by using many hidden layers such as general deep learning methods. In CMDELM-LRF, one hidden layer, which maximizes the canonical correlation between visual features and text features obtained from inspection text data, is newly inserted. Specifically, by using projections obtained by maximizing the canonical correlation as weight parameters of the hidden layer, feature transformation for extracting semantic information is realized without designing many hidden layers. This is the main contribution of this paper. Consequently, CMDELM-LRF realizes accurate deterioration level estimation from a small amount of training data.

[1]  Christoph Mertz,et al.  Vision for road inspection , 2014, IEEE Winter Conference on Applications of Computer Vision.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Ozgur Kisi,et al.  Applicability of a Fuzzy Genetic System for Crack Diagnosis in Timoshenko Beams , 2015, J. Comput. Civ. Eng..

[4]  Yung-Cheng Lai,et al.  Optimizing rolling stock assignment and maintenance plan for passenger railway operations , 2015, Comput. Ind. Eng..

[5]  Vikram Pakrashi,et al.  Texture Analysis Based Damage Detection of Ageing Infrastructural Elements , 2013, Comput. Aided Civ. Infrastructure Eng..

[6]  Gonzalo R. Arce,et al.  Multiresolution Information Mining for Pavement Crack Image Analysis , 2012 .

[7]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[8]  Peter Söderholm,et al.  Data Analysis for Condition‐Based Railway Infrastructure Maintenance , 2015, Qual. Reliab. Eng. Int..

[9]  Pierre-Luc Richard,et al.  LineScout Technology Opens the Way to Robotic Inspection and Maintenance of High-Voltage Power Lines , 2015, IEEE Power and Energy Technology Systems Journal.

[10]  Sami F. Masri,et al.  Parametric Performance Evaluation of Wavelet-Based Corrosion Detection Algorithms for Condition Assessment of Civil Infrastructure Systems , 2013, J. Comput. Civ. Eng..

[11]  Lu Sun,et al.  Weighted Neighborhood Pixels Segmentation Method for Automated Detection of Cracks on Pavement Surface Images , 2016, J. Comput. Civ. Eng..

[12]  Miki Haseyama,et al.  Distress Classification of Road Structures via Adaptive Bayesian Network Model Selection , 2017 .

[13]  Hoang-Nam Nguyen,et al.  An Automatic Approach for Accurate Edge Detection of Concrete Crack Utilizing 2D Geometric Features of Crack , 2014, J. Signal Process. Syst..

[14]  T. Fukuchi,et al.  Underfilm Corrosion of Transmission Tower Cross-Arms Service-Used in a Pacific Coast Area , 2015 .

[15]  Masaru Minagawa,et al.  PROTOTYPE DIAGNOSIS EXPERT SYSTEM WITH KNOWLEDGE REFINEMENT FUNCTION , 2001 .

[16]  Ying Zhang,et al.  A discriminative multi-class feature selection method via weighted l2, 1-norm and Extended Elastic Net , 2018, Neurocomputing.

[17]  Jianyu Chen,et al.  Supervised classification of hyperspectral images using local-receptive-fields-based kernel extreme learning machine , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

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

[19]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[20]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  Chi-Man Vong,et al.  Local Receptive Fields Based Extreme Learning Machine , 2015, IEEE Computational Intelligence Magazine.

[22]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[23]  Ayaho Miyamoto,et al.  Imaging-Based Rating for Corrosion States of Weathering Steel Using Wavelet Transform and PSO-SVM Techniques , 2014, J. Comput. Civ. Eng..

[24]  Alberto Jardón,et al.  Past, present and future of robotic tunnel inspection , 2015 .

[25]  Reginald R. Souleyrette,et al.  Optimizing the Alignment of Inspection Data from Track Geometry Cars , 2015, Comput. Aided Civ. Infrastructure Eng..

[26]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[27]  F. Tsutsumi,et al.  Automatic corrosion estimation using galvanized steel images on power transmission towers , 2009, 2009 Transmission & Distribution Conference & Exposition: Asia and Pacific.

[28]  Patrik Jonsson,et al.  Road Surface Status Classification Using Spectral Analysis of NIR Camera Images , 2015, IEEE Sensors Journal.

[29]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[30]  Yu-Chiang Frank Wang,et al.  Heterogeneous Domain Adaptation and Classification by Exploiting the Correlation Subspace , 2014, IEEE Transactions on Image Processing.

[31]  Sang-Kyun Woo,et al.  Development of the Corrosion Deterioration Inspection Tool for Transmission Tower Members , 2016 .

[32]  Qingquan Li,et al.  CrackTree: Automatic crack detection from pavement images , 2012, Pattern Recognit. Lett..

[33]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[34]  Victor C. M. Leung,et al.  Extreme Learning Machines [Trends & Controversies] , 2013, IEEE Intelligent Systems.

[35]  Zhenghao Chen,et al.  On Random Weights and Unsupervised Feature Learning , 2011, ICML.

[36]  Miki Haseyama,et al.  Automatic estimation of deterioration level on transmission towers via deep extreme learning machine based on local receptive field , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[37]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[38]  Nigel Waters,et al.  Review of remote sensing methodologies for pavement management and assessment , 2015 .

[39]  Fei-Fei Li,et al.  Improving Image Classification with Location Context , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[40]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[41]  Eduardo Zalama Casanova,et al.  Road Crack Detection Using Visual Features Extracted by Gabor Filters , 2014, Comput. Aided Civ. Infrastructure Eng..

[42]  Yimin D. Zhang,et al.  Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[43]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[44]  Tara C. Hutchinson,et al.  Improved image analysis for evaluating concrete damage , 2006 .

[45]  Xiaoming Zhang,et al.  Classify social image by integrating multi-modal content , 2018, Multimedia Tools and Applications.

[46]  Ashutosh Bagchi,et al.  Tracking of Defects in Reinforced Concrete Bridges Using Digital Images , 2016, J. Comput. Civ. Eng..

[47]  Xiaogang Wang,et al.  Medical image classification with convolutional neural network , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

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

[49]  Peng Li,et al.  Automatic diagnosis system of transmission line abnormalities and defects based on UAV , 2016, 2016 4th International Conference on Applied Robotics for the Power Industry (CARPI).