A generation method of insulator region proposals based on edge boxes

Abstract

High-quality insulator region proposals play important roles in the process of transmission line inspection images. A generation method of insulator region proposals based on edge boxes is proposed in this paper, and edge boxes are applied to the localization of insulators in inspection images creatively. We take a series of operations to generate insulator region proposals: K-means cluster is used on curvature scale space (CSS) points extracted from edge images, the most appropriate cluster number is chosen, and the circle is drawn on the insulator subclass. We consider the characteristics of insulators’ edge images, and combine these characteristics with edge boxes. As a result, more insulator region proposals are displayed. The experimental results show that our method can effectively reduce the interference area, meanwhile, has high quality of region proposals with fast calculation speed.

References

[1] HuW. Study on New Technology of Fault Diagnosis for Electrical Equipment Based on Intelligent Information Fusion, 2005,

[2] LiL. Research on the Technology and Application of Power Line Inspection with Unmanned Aerial Vehicles, 2012,

[3] WangH, ZhuM, LinC-b, ChenD-b. Optoelectronics Letters, 2017, 13: 151

[4] HosangJ, BenensonR, DollarP, SchieleB. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 38: 814

[5] HosangJ, BenensonR, SchieleB. How Good are Detection Proposals, Really? Computer Science, 2014,

[6] EveringhamM, GoolL V, WilliamsC K I, WinnJ, ZissermanA. International Journal of Computer Vision, 2010, 88: 303

[7] DengJ, DongW, SocherR, LiL, LiK, LiF. ImageNet: A large-Scale Hierarchical Image Database, 2009, 248

[8] GirshickR, DonahueJ, DarrellT, MalikJ. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, 2014, 580

[9] KoenE A S, JasperR R U, TheoG, ArnoldW M S. IEEE Computer Society, 2011, 104: 1879

[10] KrizhevskyA, SutskeverI, HintonG E. International Conference on Neural Information Processing Systems, 2012, 25: 1097

[11] HeK, ZhangX, RenS, SunJ. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37: 1904

[12] GirshickR. Fast R-CNN, Computer Science, 2015,

[13] RenS, HeK, GirshickR, SunJ. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 39: 1137

[14] ZitnickC L, DollarP. Edge Boxes: Locating Object Proposals from Edges, 2014, 391

[15] ChengM M, ZhangZ, LinW Y, TorrP. BING: Binarized Normed Gradients for Objectness Estimation at 300fps, 2014, 3286

[16] ZhaoQ, LiuZ, YinB. Cracking BING and beyond, 2014,

[17] ZhuL, ChenY, YuilleA, FreemanW. Computer Vision and Pattern Recognition, 2010, 119: 1062

[18] MokhtarianF, SuomelaR. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20: 1376

[19] SUNJ-d, GUOQ-q, ZHANGZ-s. Opto-Electronic Engineering, 2009, 36: 78

[20] LuY, ZhouY, ChenH-h. Optoelectronics Letters, 2016, 12: 77