首页 > 论文 > 光学学报 > 38卷 > 9期(pp:915001--1)

基于离线学习的野外架空地线检测算法

Field Ground Wire Detection Algorithm Based on Off-Line Learning Method

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

野外复杂环境下地线检测是高压输电线路巡检机器人自主越障的关键技术之一,光照变化和地线表面新旧程度是影响架空地线检测准确率的关键因素。针对这一问题,提出一种基于离线学习的野外架空地线检测算法。离线训练阶段,首先采用自适应同态滤波器对输入样本进行光照补偿,然后提取样本的局部二值模式直方图特征,结合离线学习算法支持向量机训练得到二类分类器;在线检测阶段,首先对样本分块,分类得到候选地线样本块,然后采用随机采样一致性算法去除误检块,拟合得到地线在图像坐标系中的位置参数。在野外新旧程度不同的线路上进行的大量实验表明,该方法对光照变化有良好的适应性,能较准确地检测不同新旧程度的架空地线,为后续的地线空间定位与抓线控制奠定了基础。

Abstract

Overhead ground wire detection under complex field environment is one of the key technologies of automatic obstacle surmounting for a high voltage transmission line inspection robot. The varying illumination and wire surface condition are the key factors affecting the detection accuracy. To address the problem, a field wire detection algorithm based on off-line learning is proposed. In the training phase, the adaptive homomorphic filter is applied to the input samples to compensate illumination, followed by local binary pattern histogram feature extraction and support vector machine training to get a binary classifier. In the on-line detection phase, each sample is divided into patches, followed by classification through the trained classifier to get the wire patch candidates. Then, the random sample consensus algorithm is adopted to remove mistakenly identified patches, and the remaining candidates are fitted into a line to get the wire parameters in the image coordinate system. The results of a number of experiments with field surroundings and different wires show that the proposed method has good adaptability to varying illumination and can detect both old and new wire accurately. Furthermore, this work has laid a solid foundation for the subsequent three dimensional positioning and grasping control of the ground wire.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.0915001

所属栏目:机器视觉

基金项目:广东省机器人专项(2015B090922007)、广东省佛山市科技创新团队项目(2015IT100143)

收稿日期:2018-03-16

修改稿日期:2018-04-03

网络出版日期:2018-04-09

作者单位    点击查看

叶旭辉:武汉大学动力与机械学院, 湖北 武汉 430072
吴功平:武汉大学动力与机械学院, 湖北 武汉 430072
黄乐:武汉大学动力与机械学院, 湖北 武汉 430072
樊飞:武汉大学动力与机械学院, 湖北 武汉 430072

联系人作者:吴功平(gpwu@whu.edu.cn)

【1】Sun C L, Wang H G, Wang L D, et al. An improved obstacle-navigation method based on extra-high voltage power transmission line for inspection robot[J]. Robot, 2006, 28(4): 380-384.
孙翠莲, 王洪光, 王鲁单,等.一种改进的超高压输电线路巡检机器人越障方法[J]. 机器人, 2006, 28(4): 380-384.

【2】Han S S, Jangmyung L. Path-selection control of a power line inspection robot using sensor fusion[C]. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems,2008, 7: 335-348.

【3】Richard P, Pouliot L, Montambault S. Introduction of a LIDAR-based obstacle detection system on the LineScout power line robot[C]. 2014 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2014: 1734-1740.

【4】Zhang Y C, Liang Z Z, Tan M, et al. Visual servo control of obstacles negotiation for overhead power line inspection robot[J]. Robot,2007, 29(2): 111-116.
张运楚, 梁自泽, 谭民, 等. 架空输电线路巡线机器人越障视觉伺服控制[J]. 机器人, 2007, 29(2): 111-116.

【5】Wang L D, Wang H G, Fang L J, et al. Visual servo-based line-grasping control for power transmission line inspection robot[J]. Robot, 2007, 29(5): 451-455.
王鲁单, 王洪光, 房立金, 等. 基于视觉伺服的输电线巡检机器人抓线控制[J]. 机器人, 2007, 29(5): 451-455.

【6】Wang C, Sun W. Line-grasping control for the deicing robot on high voltage transmission line[J]. Journal of Mechanical Engineering, 2011, 47(9): 8-15.
王聪, 孙炜. 高压输电线路除冰机器人抓线运动控制[J]. 机械工程学报, 2011, 47(9): 8-15.

【7】Guo W B, Wang H G, Jiang Y, et al. Visual servo control for automatic line-grasping of a power transmission line inspection robot[J]. Robot, 2012, 34(5): 620-627.
郭伟斌, 王洪光, 姜勇, 等. 一种输电线巡检机器人的自动抓线视觉伺服控制[J]. 机器人, 2012, 34(5): 620-627.

【8】Wang W, Wu G P, Bai Y C, et al. Hand-eye-vision based control for an inspection robot′s autonomous line grasping[J]. Journal of Central South University, 2014, 21(6): 2216-2227.

【9】Cao W M. Research on visual control methods for high voltage transmission line deicing robot[D]. Changsha: Hunan University, 2014.
曹文明. 高压输电线路除冰机器人视觉控制方法研究[D]. 长沙: 湖南大学, 2014.

【10】Song Y F, Wang H G, Zhang J W. A vision-based broken strand detection method for a power-line maintenance robot[J]. IEEE Transactions on Power Delivery, 2014, 29(5): 2154-2161.

【11】Gonzalez R C, Woods R E. Digital image processing[M]∥Ruan Q Q, Ruan Y Z, Transl. 3rd ed. Beijing: Publishing House of Electronics Industry, 2011.

【12】Wang B, Li W, Yang W, et al. Illumination normalization based on Weber′s law with application to face recognition[J]. IEEE Signal Processing Letters, 2011, 18(8): 462-465.

【13】Solomon C, Breckon T. Fundamentals of digital image processing[M]. New Jersey: John Wiley & Sons Publication, 2011.

【14】Huang Y S, Li C Y. An effective illumination compensation method for face recognition[J]. Journal of Marine Science and Technology, 2013, 21(6): 647-652.

【15】Faraji M R, Qi X. Face recognition under varying illumination based on adaptive homomorphic eight local directional patterns[J]. IET Computer Vision, 2015, 9(3): 1-10.

【16】Ojala T, Pietikinen M, Menp T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

【17】Yuan L, Chen F, Zhou L, et al. Improve scene classification by using feature and kernel combination[J]. Neurocomputing, 2015, 170: 213-220.

【18】Zhou S R, Yin J P, Zhang J M, et al. Local binary pattern (LBP) and local phase quantization (LBQ) based on Gabor filter for face representation[J]. Neurocomputing, 2013, 116:260-264.

【19】Liao J S, Wang L G. Hyperspectral image classification method based on fusion with two kinds of spatial information[J]. Laser & Optoelectronics Progress, 2017, 54(8): 081002.
廖建尚, 王立国. 两类空间信息融合的高光谱图像分类方法[J]. 激光与光电子学进展, 2017, 54(8): 081002.

【20】Yang M, Zhang B, Song Y L. The application of support vector machine based on optimized kernel function in people detection[J]. Laser & Optoelectronics Progress, 2018, 55(4): 041001.
杨萌, 张葆, 宋玉龙. 基于优化核函数支持向量机在行人检测中的应用[J]. 激光与光电子学进展, 2018, 55(4): 041001.

【21】Jin J J, Lu W L, Guo X T, et al. Position registration method of simultaneous phase-shifting interferograms based on SURF and RANSAC algorithm[J]. Atca Optica Sinica, 2017, 37(10): 1012002.
靳京京, 卢文龙, 郭小庭,等.基于SURF和RANSAC算法的同步相移干涉图位置配准方法[J]. 光学学报, 2017, 37(10): 1012002.

【22】Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems & Technology, 2011, 2(3): 27.

引用该论文

Ye Xuhui,Wu Gongping,Huang Le,Fan Fei. Field Ground Wire Detection Algorithm Based on Off-Line Learning Method[J]. Acta Optica Sinica, 2018, 38(9): 0915001

叶旭辉,吴功平,黄乐,樊飞. 基于离线学习的野外架空地线检测算法[J]. 光学学报, 2018, 38(9): 0915001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF