Deep Multitask Learning for Railway Track Inspection

Railroad tracks need to be periodically inspected and monitored to ensure safe transportation. Automated track inspection using computer vision and pattern recognition methods has recently shown the potential to improve safety by allowing for more frequent inspections while reducing human errors. Achieving full automation is still very challenging due to the number of different possible failure modes, as well as the broad range of image variations that can potentially trigger false alarms. In addition, the number of defective components is very small, so not many training examples are available for the machine to learn a robust anomaly detector. In this paper, we show that detection performance can be improved by combining multiple detectors within a multitask learning framework. We show that this approach results in improved accuracy for detecting defects on railway ties and fasteners.

[1]  Pavel Babenko,et al.  Visual inspection of railroad tracks. , 2011 .

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[4]  Saman A. Zonouz,et al.  Identification Using Encrypted Biometrics , 2013, CAIP.

[5]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[6]  Rama Chellappa,et al.  Discrete shearlet transform on GPU with applications in anomaly detection and denoising , 2014, EURASIP Journal on Advances in Signal Processing.

[7]  Zhiguo Jiang,et al.  Broken Railway Fastener Detection Based on Adaboost Algorithm , 2010, 2010 International Conference on Optoelectronics and Image Processing.

[8]  Hui Zhao,et al.  An Efficient Direction Field-Based Method for the Detection of Fasteners on High-Speed Railways , 2011, Sensors.

[9]  Ching-Lung Liao,et al.  Visual Recognition System of Elastic Rail Clips for Mass Rapid Transit Systems , 2007 .

[10]  Sadananda Sahu,et al.  DELAYED ETTRINGITE FORMATION IN SWEDISH CONCRETE RAILROAD TIES , 2004 .

[11]  Narendra Ahuja,et al.  Automated Visual Inspection of Railroad Tracks , 2013, IEEE Transactions on Intelligent Transportation Systems.

[12]  Rama Chellappa,et al.  Material classification and semantic segmentation of railway track images with deep convolutional neural networks , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[13]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Rubel Biswas,et al.  Automatic detection of defective rail anchors , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[15]  David G. Lowe,et al.  Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration , 2009, VISAPP.

[16]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

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

[20]  A. Distante,et al.  Visual recognition of missing fastening elements for railroad maintenance , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[21]  Long Chen,et al.  Automatic Fastener Classification and Defect Detection in Vision-Based Railway Inspection Systems , 2014, IEEE Transactions on Instrumentation and Measurement.

[22]  M. Singh,et al.  Autonomous Rail Track Inspection using Vision Based System , 2006, 2006 IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety.

[23]  Ying Li,et al.  Enhanced rail component detection and consolidation for rail track inspection , 2012, 2012 IEEE Workshop on the Applications of Computer Vision (WACV).

[24]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[25]  Michael D.A. Thomas,et al.  The effect of fly ash composition on the expansion of concrete due to alkali-silica reaction , 2000 .

[26]  Ali Tajaddini,et al.  A Machine Vision System for Automated Joint Bar Inspection From a Moving Rail Vehicle , 2007 .

[27]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[28]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[29]  Ettore Stella,et al.  A Real-Time Visual Inspection System for Railway Maintenance: Automatic Hexagonal-Headed Bolts Detection , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[30]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[31]  Jack Mostow,et al.  Direct Transfer of Learned Information Among Neural Networks , 1991, AAAI.

[32]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[34]  Matti Pietikäinen,et al.  Rotation Invariant Image Description with Local Binary Pattern Histogram Fourier Features , 2009, SCIA.

[35]  B. V. Vijaya Kumar,et al.  Unconstrained correlation filters. , 1994, Applied optics.

[36]  Ying Li,et al.  Rail Component Detection, Optimization, and Assessment for Automatic Rail Track Inspection , 2014, IEEE Transactions on Intelligent Transportation Systems.

[37]  Rama Chellappa,et al.  Robust Fastener Detection for Autonomous Visual Railway Track Inspection , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[38]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

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

[41]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[42]  Ettore Stella,et al.  A GPU-based vision system for real time detection of fastening elements in railway inspection , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[43]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.