[1]汤 丹,方 挺.基于核相关滤波的多尺度绝缘子目标跟踪[J].电瓷避雷器,2019,(06):205-209.[doi:10.16188/j.isa.1003-8337.2019.06.033]
 TANG Dan,FANG Ting.Multi-Scale Insulator Target Tracking Based on Kernel Correlation Filters[J].,2019,(06):205-209.[doi:10.16188/j.isa.1003-8337.2019.06.033]
点击复制

基于核相关滤波的多尺度绝缘子目标跟踪()
分享到:

《电瓷避雷器》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年06期
页码:
205-209
栏目:
绝缘子
出版日期:
2019-12-10

文章信息/Info

Title:
Multi-Scale Insulator Target Tracking Based on Kernel Correlation Filters
作者:
汤 丹 方 挺
(安徽工业大学电气与信息工程学院, 安徽 马鞍山 243000)
Author(s):
TANG Dan FANG Ting
(School of electrical and information engineering, Anhui university of technology, Maanshan 243000, China)
关键词:
绝缘子目标 视频跟踪 核相关滤波 尺度估计
Keywords:
insulator target video tracking kernel correlation filters scale estimation
DOI:
10.16188/j.isa.1003-8337.2019.06.033
摘要:
针对输电线路巡检视频中的绝缘子目标跟踪背景复杂,不能适应绝缘子尺度变化的问题,提出了一种基于核相关滤波的多尺度绝缘子目标跟踪算法。该算法首先提取绝缘子Hog特征,通过最小化决策函数来训练一个分类器,得出绝缘子目标位置,最后引入多尺度估计方法,来确定绝缘子目标的大小,从而提高了绝缘子跟踪的精度。实验结果表明,本文提出的跟踪算法能够适应绝缘子尺度变化且与传统Camshift的算法相比,具有较好的跟踪性能。
Abstract:
In view of the complexity of tracking background and difficult to adapt to the scale change in the transmission line inspection video, a multi-scale insulator tracking algorithm based on kernel correlation filtering is proposed. The algorithm first extracts the Hog characteristics of insulators, then trains a classifier by minimizing the decision function, and obtains the position of the insulator target. Finally, a multi-scale estimation method is introduced to determine insulator target size and improve the accuracy of insulator tracking. The experimental results show that the algorithm proposed in this paper can adapt to the change of insulator scale and has better tracking performance compared with the traditional Camshift algorithm.

参考文献/References:

[1] 蒋兴良,赵世华,毕茂强,等.污秽绝缘子闪络特性与泄漏电流特性研究[J].中国电机工程学报,2013,33(31):220-226. JIANG Xingliang, ZHAO Shihua, BI Maoqiang, et al. Research on flashover performance and leakage current performance of polluted insulators[J]. Proceedings of the CSEE, 2013, 33(31): 220-226.
[2] ZHAI YongJie, WANG Di, WU Yang, et al. Two-stage recognition method of aerial insulator images based on skeleton extraction[J]. Journal of North China Electric Power University(Natural science edition), 2015(3):105-110.
[3] MENENDEZ O A, PEREZ M, AUAT CHEEIN F A. Vision based inspection of transmission lines using unmanned aerial vehicles[C].2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems(MFI). 2016: 412-417.
[4] 李建峰,段宇涵,王仓继,等.无人机在输电线路巡检中的应用 [J]. 电网与清洁能源,2017,33(8):62-65. LI Jianfeng, DUAN Yuhan, WANG Cangji, et al.Application of the unmanned aerial vehicle in the transmission line inspection [J]. Power System and Clean Energy,2017,33(8):62-65.
[5] 包万敏,王伟,李涛.智能电网传输线路的无线检测网络设计[J]. 电网与清洁能源,2017,33(12):52-58. BAO Wanmin, WANG Wei, LI Tao.Design of wireless detection network for smart grid transmission line [J]. Power System and Clean Energy,2017,33(12):52-58.
[6] 胡年平,徐芳敏,谢宁,等.改进小生境粒子群算法应用于电网故障诊断[J]. 电网与清洁能源,2018,34(1):09-16. HU Nianping, XU Fangmin,XIE Ning,et al.Application of improved niching particle swarm optimization algorithm in power system fault diagnosis[J]. Power System and Clean Energy,2018,34(1):09-16.
[7] 王国良,刘金国.基于粒子滤波的多自由度运动目标跟踪[J].光学精密工程,2011, 19(4):864-869. WANG Guoliang, LIU Jinguo. Moving object tracking with multi-degree-of-freedom based on particle filters[J]. Optics and Precision Engineering, 2011, 19(4): 864-869.
[8] 卢璇,雷航,郝宗波.联合多特征的自动CamShift跟踪算法[J].计算机应用,2010, 30(3):650-652. LU Xuan, LEI Hang, HAO Zongbo. Automatic CamShift tracking algorithm based on multi-feature[J]. Journal of Computer Applications, 2010, 30(3): 650-652.
[9] GAO Changxin, CHEN Feifei, YU Jingang, et al. Robust visual tracking using Exemplar-Based detectors[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(2): 300-312.
[10] YAN Shujia, WANG Shicong, TONG Meisong. Identification of high-temperature region for insulators based on BP neural network[C].2017 Progress in Electromagnetics Research Symposium - Fall(PIERS - FALL). 2017: 2131-2135.
[11] 苑津莎,崔克彬,李宝树.基于 ASIFT 算法的绝缘子视频图像的识别与定位[J].电测与仪表,2015, 52(7):106-112. YUAN Jinsha, CUI Kebin, LI Baoshu. Identification and location of insulator video images based on ASIFT algorithm[J]. Electrical Measurement & Instrumentation, 2015, 52(7): 106-112.
[12] 李岩.基于HOG特征和SVM的绝缘子识别与定位[J].交通运输工程与信息学报,2015, 13(4):53-60. LI Yan. Insulator location and recognition algorithm based on HOG characteristics and SVM[J]. Journal of Transportation Engineering and Information, 2015, 13(4): 53-60.
[13] 郭金鑫,陈玮.基于HOG多特征融合与随机森林的人脸识别[J].计算机科学,2013, 40(10):279-282. GUO Jinxin, CHEN Wei. Face recognition based on HOG multi-feature fusion and random forest[J]. Computer Science, 2013, 40(10): 279-282.

备注/Memo

备注/Memo:
收稿日期:2018-04-20 作者简介:汤丹(1994—),女,硕士,主要研究方向为图像处理。 基金项目:基于图像处理的输电线路故障诊断(编号:51007002)。
更新日期/Last Update: 2019-12-10