Computer vision–based automatic rod-insulator defect detection in high-speed railway catenary system

Maintenance of catenary system is a crucial task for the safe operation of high-speed railway systems. Catenary system malfunction could interrupt railway service and threaten public safety. This article presents a computer vision algorithm that is developed to automatically detect the defective rod-insulators in a catenary system to ensure reliable power transmission. Two key challenges in building such a robust inspection system are addressed in this work, the detection of the insulators in the catenary image and the detection of possible defects. A two-step insulator detection method is implemented to detect insulators with different inclination angles in the image. The sub-images containing cantilevers and rods are first extracted from the catenary image. Then, the insulators are detected in the sub-image using deformable part models. A local intensity period estimation algorithm is designed specifically for insulator defect detection. Experimental results show that the proposed method is able to automatically and reliably detect insulator defects including the breakage of the ceramic discs and the foreign objects clamped between two ceramic discs. The performance of this visual inspection method meets the strict requirements for catenary system maintenance.

[1]  Anthony Choi,et al.  Monaural Sound Localization Based on Reflective Structure and Homomorphic Deconvolution , 2017, Sensors.

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

[3]  Aaron E. Rosenberg,et al.  A comparative performance study of several pitch detection algorithms , 1976 .

[4]  Huaizhong Li,et al.  Gradient-guided color image contrast and saturation enhancement , 2017 .

[5]  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.

[6]  Dah-Jye Lee,et al.  High-speed railway rod-insulator detection using segment clustering and deformable part models , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[7]  Rama Chellappa,et al.  Deep Multitask Learning for Railway Track Inspection , 2015, IEEE Transactions on Intelligent Transportation Systems.

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

[9]  M. Ross,et al.  Average magnitude difference function pitch extractor , 1974 .

[10]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Mehmet Karakose,et al.  A new computer vision approach for active pantograph control , 2013, 2013 IEEE INISTA.

[12]  Tong Zheng,et al.  A new detection and recognition method for optical fiber pre-warning system , 2017 .

[13]  Xiaofeng Liu,et al.  Location Identification of Closed Crack Based on Duffing Oscillator Transient Transition , 2018 .

[14]  Ye Zhang,et al.  Automatic identification and location technology of glass insulator self-shattering , 2017, J. Electronic Imaging.

[15]  Sun-Young Hwang,et al.  An improved Haar-like feature for efficient object detection , 2014, Pattern Recognit. Lett..

[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]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[18]  Hui Li,et al.  A Robust and Efficient Algorithm for Tool Recognition and Localization for Space Station Robot , 2014 .

[19]  Zhigang Liu,et al.  A High-Precision Detection Approach for Catenary Geometry Parameters of Electrical Railway , 2017, IEEE Transactions on Instrumentation and Measurement.

[20]  Di Wang,et al.  Fault detection of insulator based on saliency and adaptive morphology , 2017, Multimedia Tools and Applications.

[21]  Jubai An,et al.  An Active Contour Model Based on Texture Distribution for Extracting Inhomogeneous Insulators From Aerial Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Robert B. Randall,et al.  A history of cepstrum analysis and its application to mechanical problems , 2017 .

[23]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[24]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[25]  Bo Li,et al.  Ship Detection From Optical Satellite Images Based on Saliency Segmentation and Structure-LBP Feature , 2017, IEEE Geoscience and Remote Sensing Letters.

[26]  Qingyong Li,et al.  A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads , 2012, IEEE Transactions on Instrumentation and Measurement.

[27]  Hideki Kawahara,et al.  YIN, a fundamental frequency estimator for speech and music. , 2002, The Journal of the Acoustical Society of America.

[28]  Sandeep Kumar.  Performance Evaluation of Novel AMDF-Based Pitch Detection Scheme , 2016 .

[29]  Horst Bischof,et al.  Visual Recognition and Fault Detection for Power Line Insulators , 2014 .

[30]  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).

[31]  Hanseok Ko,et al.  Video-Based Dynamic Stagger Measurement of Railway Overhead Power Lines Using Rotation-Invariant Feature Matching , 2015, IEEE Transactions on Intelligent Transportation Systems.

[32]  Zhu Lianqing,et al.  Golf video tracking based on recognition with HOG and spatial–temporal vector , 2017 .