Abstract
In this paper, we propose a learning-based real-time method to recognize and segment an overhead ground wire (OGW) from an image, which is mainly applied to the multi-scale features in a cluttered environment. The recognition and segmentation are implemented under the framework of conditional generative adversarial nets. The generator is an end-to-end convolutional neural network (CNN) with skip connection. The discriminator is a multi-stage CNN and learns the loss function to train the generator. The OGW is recognized and shown in the downsampling visual saliency map. Thus, the location and existence of OGW are verified, which is crucial for the detection in the cluttered environment with structural lines. Detailed experiments and comparisons are performed on real-world images to demonstrate that the proposed method significantly outperforms the traditional method. Additionally, the optimized network achieves approximately 200 fps on a graphics card (GTX970) and 30 fps on an embedded platform (Jetson TX1).
Similar content being viewed by others
References
Jaka K, Pernus F, Likar B (2010) A survey of mobile robots for distribution power line inspection. IEEE Trans Power Deliv 25(1):485–493
Pagnano A, Höpf M, Teti R (2013) A roadmap for automated power line inspection maintenance and repair. Procedia Cirp 12:234–239
Pouliot N, Richard PL, Montambault S (2015) LineScout technology opens the way to robotic inspection and maintenance of high-voltage power lines. IEEE Power Energy Technol Syst J 2(1):1–11
Matikainena L, Lehtomäkia M, Ahokasa E, Hyyppäa J, Karjalainena M, Jaakkolaa A, Kukkoa A, Heinonenb T (2016) Remote sensing methods for power line corridor surveys. ISPRS J Photogramm Remote Sens 119:10–31
Jones DI, Earp GK (2001) Camera sightline pointing requirements for aerial inspection of overhead power lines. Electr Power Syst Res 57(2):73–82
Hydro-Québec (2017) Drone used to inspect power transmission systems. YouTube. http://mir-innovation.hydroquebec.com/mir-innovation/en/medias-news.html. Accessed 10 Oct 2017
SKIVE AVIATION AIRBORNE ROBOTICS (2015) SKIVE powerline robot. YouTube. http://www.skive.aero/index.php/powerline-inspection. Accessed 10 Oct 2017
Chang W, Yang G, Zhi J, Liang Z, Cheng L, Zhou C (2017) Development of a power line inspection robot with hybrid operation modes. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), pp 973–978
Zhao D, Yang G, Li E, Liang Z (2013) Design and its visual servoing control of an inspection robot for power transmission lines View Document. In: 2013 IEEE international conference on robotics and biomimetics (ROBIO), pp 546–551
Song Y, Wang H, Zhang J (2014) A vision-based broken strand detection method for a power-line maintenance robot. IEEE Trans Power Deliv 29(5):2154–2161
Pouliot N, Richard P, Montambault S (2012) LineScout power line robot: characterization of a UTM-30LX LIDAR system for obstacle detection. In: 2012 IEEE/RSJ international conference on intelligent robots and systems (IROS), pp 4327–4334
Richard P, Pouliot N, Montambault S (2014) Introduction of a LIDAR-based obstacle detection system on the LineScout power line robot. In: 2014 IEEE/ASME international conference on advanced intelligent mechatronics (AIM), pp 1734–1740
Ziegler V, Schubert F, Schulte B, Giere A, Koerber R (2013) Helicopter near-field obstacle warning system based on low-cost millimeter-wave radar technology. IEEE Trans Microw Theory Tech 61(1):658–665
Deng S, Li P, Zhang J, Yang J (2012) Power line detection from synthetic aperture radar imagery using coherence of co-polarisation and cross-polarisation estimated in the Hough domain. IET Radar Sonar Navig 6(9):873–880
Luo X, Zhang J, Cao X, Yan P, Li X (2014) Object-aware power line detection using color and near-infrared images. IEEE Trans Aerosp Electron Syst 50(2):1374–1389
Shan H, Zhang J, Cao X (2015) Power line detection using spatial contexts for low altitude environmental awareness. In: Integrated communication navigation and surveillance conference (ICNS), w2–1–w2–10
Yetgin ÖE, Sentürk Z, Gerek ÖN (2015) A comparison of line detection methods for power line avoidance in aircrafts. In: International conference on electrical and electronics engineering (ELECO), pp 241–245
Song B, Li X (2014) Power line detection from optical images. Neurocomputing 129:350–361
Gioi RG, Jakubowicz J, Morel J, Randall G (2012) LSD: a line segment detector. Image Process Line 2:35–55
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: European conference on computer vision (ECCV), pp 21–37
Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentation. arXiv:1606.02147
Pan J, Ferrer C, McGuinness K, Connor NE, Torres J, Sayrol E, Nieto X (2017) SalGAN: visual saliency prediction with generative adversarial networks. arXiv:1701.01081
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (NIPS), pp 91–99
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788
He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. arXiv:1703.06870
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Isola P, Zhu J, Zhou T, Efros A (2016) Image-to-image translation with conditional adversarial Networks. arXiv:1611.07004
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1026–1034
Chetlur S, Woolley C, Vandermersch P, Cohen J, Tran J, Catanzaro B, Shelhamer E (2014) cuDNN: efficient primitives for deep learning. arXiv:1410.0759
Larsen ABL, Sønderby SK, Larochelle H, Winther O (2015) Autoencoding beyond pixels using a learned similarity metric. arXiv:1512.09300
Chan T, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2014) PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 50(2):1374–1389
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Grant No. 61403374)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chang, W., Yang, G., Li, E. et al. Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition. Neural Process Lett 48, 1789–1800 (2018). https://doi.org/10.1007/s11063-018-9799-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-018-9799-3