Transmission Line Insulators Detection Based on KAZE Algorithm

Abstract:

Transmission Line obstacle detection technology is one of the hot spots of computer vision and transmission line inspection robot system.As the most common obstacle of inspection robot,correctly identify of insulators can help improve the reliability and accuracy of self-inspection. Low robustness of traditional detection algorithm can not meet the requirements on insulators detection when dealing with complex environment. To solve the above problem, a transmission line insulators detection method based on KAZE algorithm is given. The feature extraction is done in the nonlinear scale space, and feature vectors are formed with M-SURF algorithm, what’s more, feature vectors detecting is worked through the nearest neighbor algorithm as matching criteria and RANSC generated algorithm. Experimental results show that the effect of insulators detection algorithm based on KAZE detect faster and also make a good performance on accuracy and robustness.

• Periodical: Advanced Materials Research (Volume 936)
• Pages: 2184-2189
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.936.2184
• Online since: June 2014
• Authors: Dan Li*, Meng Zhang, Zu Bing Tong
• Keywords: Insulators Detection, KAZE Algorithm, Transmission Line

References

[1] Zuo Qi, Xie Zhi, Liang Zize, Development and Application of Transmission Line Inspection Robot,J. Robot Technique and Application. 3(2007)37-42.

[2] Zhang Yunchu, Liang Zize, Fu Siyao, Structure Constrained Obstacle Recognition for Transmission Line Inspection Robot,J. Robot. 1(2007)1-6.

DOI: 10.1109/coginf.2008.4639195

[3] Guo Weibin, Wang Hongguan, Jiang Yong, Obstacle Navigation Planning for a Power Transmission Line Inspection Robot,J. Robot. 34(2010)506-512.

DOI: 10.3724/sp.j.1218.2012.00505

[4] Jaka Katrasnik, Franjo Pernus, Bostjan Likar. A Survey of Mobile Robots for Distribution Power Line Inspection,J. IEEE Transactions On Power Delivery. 25(2010)485-493.

DOI: 10.1109/tpwrd.2009.2035427

[5] Sun Fengjie, Yang Zhenhuan, Li Yuanyuan, Methods of transmission line target recognition, J. Journal of Image and Graphics. 17(2012)349-356.

[6] MARTIN H, DE LOPE J, MARAVALLD. The KNN-TD reinforce-ment learning algorithm, in: Proceedings of the 3rd International Work Conference on the Interplay Between Natural and Artificial Computation. Spain: Springer, 2009: 305 – 314.

[7] Pablo F. Alcantarilla, Adrien, Andrew J. Davison, KAZE Feature. ECCV, (2012).

[8] Jiang Murong, Guo Ruilin, Zhang Zexian, Parallel Implementation for AOS Scheme on a Dual-core Cluster,J. International Conference on Intelligent Networks and Intelligent Systems, 3(2010).

DOI: 10.1109/icinis.2010.111

[9] Lowe D. Distinctive image features from scale-invariant keypoints,J. Inrl.J. of Computer Vision, 60(2004)91-110.

DOI: 10.1023/b:visi.0000029664.99615.94