access icon free Real-time segmentation of various insulators using generative adversarial networks

© The Institution of Engineering and Technology
Received 23/11/2017, Accepted 02/02/2018, Revised 12/01/2018, Published 02/02/2018

The conventional inspection of fragile insulators is critical to grid operation and insulator segmentation is the basis of inspection. However, the segmentation of various insulators is still difficult because of the great differences in colour and shape, as well as the cluttered background. Traditional insulator segmentation algorithms need many artificial thresholds, thereby limiting the adaptability of algorithms. A compact end-to-end neural network, which is trained in the framework of conditional generative adversarial networks, is proposed for the real-time pixel-level segmentation of insulators. The input image is mapped to a visual saliency map, and various insulators with different poses are filtered out at the same time. The proposed two-stage training and empty samples are also used to improve the segmentation quality. Extensive experiments and comparisons are performed on many real-world images. The experimental results demonstrate superior segmentation and real-time performance. Meanwhile, the effectiveness of the proposed training strategies and the trade-off between performance and speed are analysed in detail.

Inspec keywords: neural nets; power engineering computing; insulators; image segmentation

Other keywords: compact end-to-end neural network; insulator segmentation algorithm; segmentation quality; visual saliency map; real-time pixel-level segmentation; generative adversarial networks; artificial thresholds; proposed two-stage training; cluttered background

Subjects: Power engineering computing; Power line supports, insulators and connectors

References

    1. 1)
      • 12. Liu, Y., Yong, J., Liu, L., et al: ‘The method of insulator recognition based on deep learning’. Int. Conf. on in Applied Robotics for the Power Industry (CARPI), Jinan, China, October 2016, pp. 1–5.
    2. 2)
      • 16. Wu, Q., An, J.: ‘An active contour model based on texture distribution for extracting inhomogeneous insulators from aerial images’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (6), pp. 3613–3626.
    3. 3)
      • 34. Chen, L., Papandreou, G., Kokkinos, I., et al: ‘Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs’, arXiv: 1606.00915, 2016.
    4. 4)
      • 22. Paszke, A., Chaurasia, A., Kim, S., et al: ‘ENet: A deep neural network architecture for real-time semantic segmentation’, arXiv: 1606.02147, 2016.
    5. 5)
      • 28. Zeiler, M.D., Krishnan, D., Taylor, G.W., et al: ‘Deconvolutional networks’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, June 2010, pp. 2528–2535.
    6. 6)
      • 27. He, K., Zhang, X., Ren, S., et al: ‘Delving deep into rectifiers: surpassing human-level performance on ImageNet classification’. IEEE Int. Conf. on Computer Vision (ICCV), Santiago, Chile, December 2015, pp. 1026–1034.
    7. 7)
      • 6. Murthy, V., Tarakanath, K., Mohanta, D., et al: ‘Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM)’, IEEE Trans. Dielectr. Electr. Insul., 2010, 17, (1), pp. 89–99.
    8. 8)
      • 30. Pathak, D., Krahenbuhl, P., Donahue, J., et al: ‘Context encoders: feature learning by inpainting’, arXiv: 1604.07379, 2016.
    9. 9)
      • 35. Chandra, S., Kokkinos, I.: ‘Fast, exact and multi-scale inference for semantic image segmentation with deep Gaussian CRFs’, arXiv: 1603.08358v1, 2016.
    10. 10)
      • 20. Pan, J., Ferrer, C.C., McGuinness, K., et al: ‘SalGAN: visual saliency prediction with generative adversarial networks’, arXiv: 1701.01081, 2017.
    11. 11)
      • 8. Zhao, Z., Xu, G., Qi, Y.: ‘Representation of binary feature pooling for detection of insulator strings in infrared images’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (5), pp. 2858–2866.
    12. 12)
      • 26. Ioffe, S., Szegedy, C.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’, arXiv: 1502.03167, 2015.
    13. 13)
      • 19. Zhang, G., Liu, Z., Han, Y.: ‘Automatic recognition for catenary insulators of high-speed railway based on contourlet transform and Chan–Vese model’, Int. J. Light Electron Opt., 2016, 127, (1), pp. 215–221.
    14. 14)
      • 10. Jabid, T., Uddin, M.Z.: ‘Rotation invariant power line insulator detection using local directional pattern and support vector machine’. Int. Conf. on Innovations in Science, Engineering and Technology (ICISET), Dhaka, Bangladesh, October 2016, pp. 1–4.
    15. 15)
      • 2. Pouliot, N., Richard, P., Montambault, S.: ‘Linescout power line robot: characterization of a UTM-30LX LIDAR system for obstacle detection’. IEEE Conf. on Intelligent Robots and Systems (IROS), Algarve, Portugal, October 2012, pp. 4327–4334.
    16. 16)
      • 9. Yao, C., Wang, J., Li, C., et al: ‘The syntactical pattern recognition for the leakage current of transmission-line insulators’, IEEE Trans. Power Deliv., 2011, 26, (4), pp. 2244–2250.
    17. 17)
      • 13. Zhao, Z., Xu, G., Qi, Y., et al: ‘Multi-patch deep features for power line insulator status classification from aerial images’. Int. Joint Conf. on Neural Networks (IJCNN), Vancouver, BC, Canada, July 2016, pp. 3187–3194.
    18. 18)
      • 18. Han, Y., Liu, Z., Le, D., et al: ‘High-speed railway rod-insulator detection using segment clustering and deformable part models’. IEEE Int. Conf. on In Image Processing (ICIP), Phoenix, AZ, USA, September 2016, pp. 3852–3856.
    19. 19)
      • 23. Badrinarayanan, V., Kendall, A., Cipolla, R.: ‘Segnet: A deep convolutional encoder-decoder architecture for image segmentation’, arXiv: 1511.00561, 2016.
    20. 20)
      • 3. Chang, W., Yang, G., Yu, J., et al: ‘Development of a power line inspection robot with hybrid operation modes’. IEEE Conf. on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017, pp. 973–978.
    21. 21)
      • 7. Zhao, Z., Liu, N., Wang, L.: ‘Localization of multiple insulators by orientation angle detection and binary shape prior knowledge’, IEEE Trans. Dielectr. Electr. Insul., 2015, 22, (6), pp. 3421–3428.
    22. 22)
      • 33. Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’, arXiv: 1411.4038, 2015.
    23. 23)
      • 4. Reddy, M., Chandra, B., Mohanta, D.: ‘A DOST based approach for the condition monitoring of 11 kV distribution line insulators’, IEEE Trans. Dielectr. Electr. Insul., 2011, 18, (2), pp. 588–595.
    24. 24)
      • 11. Yan, T., Yang, G., Yu, J.: ‘Feature fusion based insulator detection for aerial inspection’. 36th Chinese Control Conf. (CCC), Dalian, China, July 2017, pp. 195–200.
    25. 25)
      • 31. Isola, P., Zhu, J.Y., Zhou, T., et al: ‘Image-to-image translation with conditional adversarial networks’, arXiv: 1611.07004, 2016.
    26. 26)
      • 24. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, arXiv: 1409.1556, 2014.
    27. 27)
      • 1. Murthy, V.S., Gupta, S., Mohanta, D.K.: ‘Digital image processing approach using combined wavelet hidden Markov model for well-being analysis of insulators’, IET Image Process., 2011, 5, (2), pp. 171–183.
    28. 28)
      • 32. Luc, P., Couprie, C., Chintala, S., et al: ‘Semantic segmentation using adversarial networks’, arXiv: 1611.08408, 2016.
    29. 29)
      • 17. Liao, S., An, J.: ‘A robust insulator detection algorithm based on local features and spatial orders for aerial images’, IEEE Geosci. Remote Sens. Lett., 2015, 12, (5), pp. 963–967.
    30. 30)
      • 21. Lei, J., Li, G., Zhang, J., et al: ‘Continuous action segmentation and recognition using hybrid convolutional neural network-hidden Markov model’, IET Comput. Vis., 2016, 10, (6), pp. 537–544.
    31. 31)
      • 15. Wu, Q., An, J., Lin, B.: ‘A texture segmentation algorithm based on PCA and global minimization active contour model for aerial insulator images’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2012, 5, (5), pp. 1509–1518.
    32. 32)
      • 5. Reddy, M., Chandra, B., Mohanta, D.: ‘Condition monitoring of 11 kV distribution system insulators incorporating complex imagery using combined DOST-SVM approach’, IEEE Trans. Dielectr. Electr. Insul., 2013, 20, (2), pp. 664–674.
    33. 33)
      • 25. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. The IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, June 2016, pp. 770–778.
    34. 34)
      • 29. Chetlur, S., Woolley, C., Vandermersch, P., et al: ‘cuDNN: efficient primitives for deep learning’, arXiv: 1410.0759, 2014.
    35. 35)
      • 14. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Neural Information Processing Systems (NIPS), Harrah's and Harveys, Lake Tahoe, December 2012, pp. 1097–1105.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0591
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0591
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading