Abstract
The object detection method based on RCNN network model has good mobility and robustness compared with the traditional methods. Classical foreign object detection algorithms for transmission line, such as SIFT and ORB feature matching algorithms. These methods have low recognition accuracy for edge blurred images and complex background images. In view of the above deficiencies, this paper constructs a transmission line training data set based on the characteristics of the collected transmission line images, and trains the Faster R-CNN model to detect the falling objects, kites, balloons and other foreign objects in the transmission lines. The experimental results show that compared with the traditional object recognition method, Faster R-CNN not only overcomes the instability of manual extraction features, but also improves the accuracy of foreign object detection in transmission lines. It can realize the detection of foreign objects in transmission lines in complex scenes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chung K, Huang Y, Tsai S (2014) Orientation-based discrete Hough transform for line detection with low computational complexity. Appl Math Comput 237(7):430–437
Wang W et al (2015) Broken strand and foreign body fault detection method for power transmission line based on unmanned aerial vehicle image. J Comput Appl 35(2):2404–2408
Guoshun Q et al (2017) Wire breakage defect detection method in the aircraft inspection lines based on image processing technology. Heilongjiang Electric Power 39(06):522–526
Ling F, Xinbo H, Yongcan Z (2011) Transmission line icing thickness measuring based on image processing. Electric Power Autom Equip 31(10):76–80
Wang Z, Pu, Z (2009) Fault location recognition in transmission lines based on support vector machines. In: 2nd IEEE international conference on computer science and information technology. IEEE, Beijing, pp 401–404
Guo T (2017) Simple convolutional neural network on image classification. In: IEEE 2nd international conference on big data analysis (ICBDA 2017). IEEE, Beijing, pp 721–724
Ye H, Kai S, Xia Y (2014) Comparison of three different multi-scale models for transmission lines to simulate diverse transients in power systems. In: International conference on power system technology. IEEE, Chengdu, pp 355–361
Khalayli L et al (2013) Automatic inspection of outdoor insulators using image processing and intelligent techniques. In: Electrical insulation conference (EIC). IEEE, Ottawa, pp 206–209
Girshick R et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on computer vision and pattern recognition. IEEE, Columbus, pp 580–587
Ren S et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Acknowledgements
This research is partially supported by: (1) Research Foundation of Education Bureau of Jilin Province (JJKN20190710KJ). (2) Science and technology development plan project of Jilin Province under Grant no. 20180520017JH. (3) Nation Natural Science Foundation of Beijing (9174047). (4) Research Foundation of Education Bureau of Jilin Province (JJKH20180447KJ).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Guo, S., Bai, Q., Zhou, X. (2020). Foreign Object Detection of Transmission Lines Based on Faster R-CNN. In: Kim, K., Kim, HY. (eds) Information Science and Applications. Lecture Notes in Electrical Engineering, vol 621. Springer, Singapore. https://doi.org/10.1007/978-981-15-1465-4_28
Download citation
DOI: https://doi.org/10.1007/978-981-15-1465-4_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1464-7
Online ISBN: 978-981-15-1465-4
eBook Packages: EngineeringEngineering (R0)