304 / 2018-09-25 23:16:08
Development of Power Transmission Line Defects Diagnosis System for UAV Inspection based on Binocular Depth Imaging Technology
Power transmission line,Defect diagnosis sytem,Depth Imaging,Binocular stereo vision
终稿
Tianqi Mao / Zunyi Power Supply Bureau, Guizhou Power Grid Corporation
Kai Huang / Xi'an Jiaotong University
Xianwu Zeng / Zunyi Power Supply Bureau, Guizhou Power Grid Corporation
Lingran Ren / Xi'an Jiaotong University
Chuance Wang / Xi'an Jiaotong University
Shengfu Li / Zunyi Power Supply Bureau, Guizhou Power Grid Corporation
Min Zhang / Northwest University
Yu Chen / Xi'an Jiaotong University
The transmission lines are widely distributed in China. The power company spends huge manpower every year on transmission line inspection. The development of UAV technology provides a new inspection method for overhead transmission line defect inspection. Nowadays, most of the inspection images with drones are based on monocular cameras. Due to the limitation of two-dimensional images, this detection method is not ideal. Aiming at the problem that the defects of transmission lines are not ideal in the complex natural environment background, in this paper, a UAV inspection defect diagnosis system with depth imaging for transmission line is proposed.

This paper introduces the related theory of binocular stereo vision, and describes in detail related image processing techniques such as binocular camera calibration, stereo image correction, stereo matching, and image segmentation. The traditional GC stereo matching algorithm is improved, and an SGC algorithm is proposed to ensure the matching precision and shorten the operation time. The algorithm uses SAD for similarity measurement to get the initial parallax, and optimized by the method of linear interpolation, to obtain the limiting energy function item SGC algorithm. The binocular image of transmission line UAV patrol inspection is stereo-matched and disparity map is generated in gray histogram analysis. The bimodal threshold segmentation algorithm is used to segment the disparity map and a pure transmission line is obtained.

The developed system includes of several parts, such as, UAV platform with Binocular stereo vision camera, UAV flight controller, ground vehicle mobile workstation, power supply station and centralized control and management center. UAV platform includes depth imaging device, airborne data center and flight control platform. The airborne data center is used to receive, store and transmit the flight status, image data information and flight control information of the drone. The depth imaging device is used to acquire an image of the area where the transmission line is located after the camera is calibrated. The flight control platform is used to receive control commands from the drone flight controller to collect and transmit flight status information of the drone. UAV flight controller includes decoding module, data receiving module, monitoring module and flight control module. The decoding device is used to parse the received flight status of the drone from the drone platform and the drone flight control data for data processing. The data processing module is configured to process the unmanned aircraft flight state and the drone flight control data parsed by the decoding device which is used by the flight control module to correct the flight instruction and the monitoring module display. The flight control module is used to issue flight instructions and control the flight status of the drone; the monitoring module is used to display the flight status information of the drone in real time, including flight altitude, flight speed, and remaining power. Ground vehicle mobile workstation includes image data decoding module, image data processing module and transmission line defect diagnosis system. Image data decoding is an image for parsing the area of the transmission line collected by the received depth imaging device for image data processing. The image data processing module is used for image correction, image preprocessing, feature extraction, stereo matching, threshold segmentation on the image of the area where the transmission line is located. The transmission line defect diagnosis system is used to match the clean transmission line image after the threshold segmentation with the defect sample database, perform defect diagnosis, and generate a defect report.

By studying the imaging model of the binocular vision system, a set of automatic transmission line detection platform is established which greatly improve the efficiency of the inspection of the UAV transmission line. Through the system, real-time inspection of transmission lines, intelligent diagnosis of defects is performed which greatly improves the diagnosis efficiency and reduces the workload of manually finding defects.
重要日期
  • 会议日期

    04月07日

    2019

    04月10日

    2019

  • 04月10日 2019

    注册截止日期

  • 05月12日 2019

    初稿截稿日期

主办单位
IEEE电介质和电气绝缘协会
中国电工学会工程电介质专业委员会
承办单位
华南理工大学
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询