Insulator Recognition Based on Moments Invariant Features and Cascade AdaBoost Classifier

Abstract:

A method based on moments invariant features and cascade AdaBoost classifier for insulator recognition is put forward to solve the problem of poor performance of insulator recognition. At first, the insulator image is preprocessed by median filtering, dilating, eroding and Otsu thresholding. Then, for the better extraction of moments invariant features, the preprocessed insulator image is tilted correctly based on PCA (Principal Component Analysis). Next, the moments invariant features are extracted and chosen to compose complex classifier in the process of training AdaBoost. Finally, the complex AdaBoost classifiers are combined in a cascade method for insulator recognition. The results of experiments demonstrate that the proposed method can recognize the insulator from complex background in the mountainous area, and it has better robustness, accuracy and validity.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 362-367
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.362
• Online since: October 2013
• Authors: Si Yuan He, Ling Wang, Yong Xia, Yan Dong Tang*
• Keywords: Cascade AdaBoost Classifier, Insulator Recognition, Moments Invariant Features

References

[1] Y. Liu, Z.D. Qian and K.Q. Xia, Transient Response of High Voltage Transmission Lines with Drum Type Towers Based on Insulator Rupture, Journal of Vibration Engineering, Vol. 22, No. 1, pp.6-12, 2009 (In Chinese).

[2] S.Y. He, L. Lin and Y.D. Tang, The Research of Power Transmission Tower Detection Method Based on UAV, Chinese Journal of Scientific Instrument, Vol. 33, No. 8, pp.270-275, 2012 (In Chinese).

[3] W.T. Li, H.J. Fan and Y.D. Tang, Detection Algorithm of High-Voltage Line Based on Hessian Matrix, Chinese Journal of Scientific Instrument, Vol. 33, No. 8, pp.243-246, 2012 (In Chinese).

[4] Rafael Grompone von Gioi, Jérémie Jakubowicz and Jean-Michel Morel, LSD: A Fast Line Segment Detector with a False Detection Control, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 4, pp.722-732, (2010).

DOI: 10.1109/tpami.2008.300

[5] J. Zhao and C. Feng, Moving Object Detection and Segmentation Based on Adaptive Frame Difference and Level Set, Information and Control, Vol. 41, No. 2, pp.153-158, 2012 (In Chinese).

[6] D.H. Wu and C.H. Zhu, A Novel License Plate Slant Correction Method Based on Principal Component Analysis, Journal of Highway and Transportation Research and Development, Vol. 23, No. 8, pp.143-146, 2006 (In Chinese).

[7] G.H. Liu, Recognition of Porcelain Bottle Crack Based on Modified ART-2 Network and Invariant Moment, Chinese Journal of Scientific Instrument, Vol. 30, No. 7, pp.1420-1425, 2009 (In Chinese).

[8] Yoav Freund and Robert E. Schapire, Experiments with a New Boosting Algorithm, In Proceedings of the 13th Conference on Machine Learning, pp.148-156, (1996).

[9] Paul Viola and Michael Jones, Rapid Object Detection Using a Boosted Cascade of Simple Features, International Conference on Computer Vision and Pattern Recognition, pp.511-518, (2001).

DOI: 10.1109/cvpr.2001.990517

[10] X.M. Tao and P.D. Cao, The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning, Information and Control, Vol. 41, No. 1, pp.7-13, 2012 (In Chinese).