首页 > 论文 > 激光与光电子学进展 > 56卷 > 8期(pp:81006--1)

基于视觉导航的输电线杆塔方位确定方法

Methodfor Orientation Determination of Transmission Line Tower Based on Visual Navigation

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

摘要

通过分析杆塔镂空的结构特征,提出了一种基于杆塔梯度方向直方图(HOG)的由远及近杆塔部件检测方法。使用不同方位下杆塔HOG特征训练多层感知机(MLP),得到训练后的分类模型,将航拍图像输入到分类模型中识别杆塔的方位,最终实现了局部目标的检测。相比于深度学习神经网络,该方法的分类特征更加明确,更具有代表性。实验结果表明,所提方法的检测准确率比Faster RCNN(Regions with Convolutional Neural Networks)方法高27.9%,运算时间比Faster RCNN减少70.6%。所提方法适用于在开阔环境下利用无人机对杆塔方位及其局部部件的精确检测。

Abstract

A method for detecting the tower components from far to near is proposed based on the histogram of the gradient (HOG) along the tower gradient direction by analyzing the structural characteristics of hollowing-out of a tower. The multi-layer perceptron (MLP) is first trained by using the HOG feature of the tower under different orientations to obtain a trained classification model, then the aerial image is input into this classification model to identify the orientation of the tower, and the detection of a local target is finally realized. Compared with that of a deep learning neural network, the classification feature of the proposed method is clear and representative. The experimental results show that the detection accuracy of the proposed method is 27.9% higher than that of the Faster RCNN (Regions with Convolutional Neural Networks) method, but the computation time is 70.9% lower than the latter. The proposed method is suitable for the accurate detection of the tower orientation and its local parts by the unmanned aerial vehicle in an open environment.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN911.73

DOI:10.3788/LOP56.081006

所属栏目:图像处理

基金项目:国家重点研发计划(2017YFC08067)

收稿日期:2018-10-22

修改稿日期:2018-11-08

网络出版日期:2018-11-13

作者单位    点击查看

王祖武:上海大学通信与信息工程学院, 上海 200444上海先进通信与数据科学研究院, 上海 200444
韩军:上海大学通信与信息工程学院, 上海 200444上海先进通信与数据科学研究院, 上海 200444
孙晓斌:国网山东省电力公司, 山东 济南 250000
杨波:国网山东省电力公司, 山东 济南 250000

联系人作者:王祖武(wangzuwu@shu.edu.cn)

【1】Cheng W, Song Z. Power pole detection based on graph cut[C]∥2008 Congress on Image and Signal Processing, May 27-30, 2008, Sanya, Hainan, China. New York: IEEE, 2008, 3: 720-724.

【2】Han B, Shang F. A frame model of power pylon detection for UAV-based power transmission line inspection[J]. Zhejiang Electric Power, 2016, 35(4): 6-11.
韩冰, 尚方. 面向无人机输电线路巡检的电力杆塔检测框架模型[J]. 浙江电力, 2016, 35(4): 6-11.

【3】Cetin B, Bikdash M, McInerney M. Automated electric utility pole detection from aerial images[C]∥IEEE Southeastcon 2009, March 5-8, 2009, Atlanta, GA, USA. New York: IEEE, 2009: 44-49.

【4】Golightly I, Jones D. Corner detection and matching for visual tracking during power line inspection[J]. Image and Vision Computing, 2003, 21(9): 827-840.

【5】Cerón A, Mondragón I, Prieto F. Real-time transmission tower detection from video based on a feature descriptor[J]. IET Computer Vision, 2016, 11(1): 33-42.

【6】Hui X L, Bian J, Yu Y J, et al. A novel autonomous navigation approach for UAV power line inspection[C]∥2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), December 5-8, 2017, Macau, China. New York: IEEE, 2017: 634-639.

【7】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

【8】Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.

【9】Hui X L, Bian J, Zhao X G, et al. Deep-learning-based autonomous navigation approach for UAV transmission line inspection[C]∥2018 Tenth International Conference on Advanced Computational Intelligence (ICACI), March 29-31, 2018, Xiamen, China. New York: IEEE, 2018: 455-460.

【10】Lei J, Fu J P, Zhang P L. Research on flaw classification of rifle cannon bore image[J]. Laser & Optoelectronics Progress, 2011, 48(12): 121002.
雷洁, 傅建平, 张培林. 线膛火炮内膛疵病图像分类研究[J]. 激光与光电子学进展, 2011, 48(12): 121002.

【11】Xu Y, Wei Z N. An improved traffic sign image recognition algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021001.
徐岩, 韦镇余. 一种改进的交通标志图像识别算法[J]. 激光与光电子学进展, 2017, 54(2): 021001.

【12】Potena C, Nardi D, Pretto A. Effective target aware visual navigation for UAVs[C]∥2017 European Conference on Mobile Robots (ECMR), September 6-8, 2017, Paris, France. New York: IEEE, 2017: 1-7.

【13】Han J, Zhang J J, Wang B H. Method on recognizing the structure of transmission line based on perceptual organization[J]. Infrared and Laser Engineering, 2013, 42(12): 3458-3463.
韩军, 张晶晶, 王滨海. 基于感知组织的输电线路结构识别方法[J]. 红外与激光工程, 2013, 42(12): 3458-3463.

【14】Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR′05), June 20-25, 2005, San Diego, CA, USA. New York: IEEE, 2005: 886-893.

【15】Dalal N. Finding people in images and videos[D]. Grenoble: Institut National Polytechnique de Grenoble-INPG, 2006: 1-8.

【16】Wu X L, Shi Z Y, Zhong Y S. An overview of vision-based UAV navigation[J]. Journal of System Simulation, 2010, 22(s1): 62-65.
吴显亮, 石宗英, 钟宜生. 无人机视觉导航研究综述[J]. 系统仿真学报, 2010, 22(s1): 62-65.

【17】Wang Y X. Research on visual ranging and visual positioning based on electric power inspection[D]. Shanghai: Shanghai University, 2017: 17-27.
王亚先. 基于电力巡检的视觉测距与视觉定位的研究[D]. 上海: 上海大学, 2017: 17-27.

【18】Xue W L. Research of quadrotor UAV flight attitude control[D]. Shenyang: Shenyang University of Technology, 2016: 6-29.
薛伟霖. 四旋翼无人机姿态控制的研究[D]. 沈阳: 沈阳工业大学, 2016: 6-29.

【19】Deng J, Dong W, Socher R, et al. ImageNet: A large-scale hierarchical image database[C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE, 2009: 248-255.

引用该论文

Wang Zuwu,Han Jun,Sun Xiaobin,Yang Bo. Methodfor Orientation Determination of Transmission Line Tower Based on Visual Navigation[J]. Laser & Optoelectronics Progress, 2019, 56(8): 081006

王祖武,韩军,孙晓斌,杨波. 基于视觉导航的输电线杆塔方位确定方法[J]. 激光与光电子学进展, 2019, 56(8): 081006

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