A Camera-based Tracking System for Distr ibution Network Inspection Based on Unmanned Aerial Vehicles

Loading...
Thumbnail Image

Paper number

2070

Working Group Number

Conference name

CIRED 2019

Conference date

3-6 June 2019

Conference location

Madrid, Spain

Peer-reviewed

Yes

Short title

Convener

Authors

Ruicong, Zhai, Guangdong Power Grid Co.-Ltd, China
Hao, Chen, Guangdong Power Grid Co. Ltd, China
Feng, Zhang, Guangdong Power Grid Co. Ltd, China
Zhihai, Xu, Guangdong Power Grid Co. Ltd, China
Chengcheng, Yang, Wuhan huzoho Technology Co. , China

Abstract

A Camera-based Tracking System for DistributionNetwork Inspection Based on Unmanned Aerial VehiclesThe emerging technology of unmanned aerial vehicle(UAV) has become more af ordable and practicable for distribution network inspections. In this paper, wepresent and demonstrate a camera-based trackingalgorithm that achieves accurate in-air localization for distribution network inspection , In order to Reduceaccuracy of GPS positioning requirements. Specifically, our approach consists of Three stages. It first generatethe route using GPS information of towers. Followingthat, the GPS information of towers automatic updateby the camera-based SLAM algorithms. According to thenew GPS information of towers, the yaw maneuveringcommand was generated and route dynamic planning onthe basis of the pre-determined route. Meanwhile, theideal camera shooting angle for Distribution Networklines and towers is calculated, Then the control angle canbe adjusted automatically to realize the trackingprocess. While a number of localization methods arepossible (most notably avehicle dif erential GPS (DGPS)system), we chose to work with a camera-based systemfor the ubiquity of cheap, low weight and high qualitycamera systems means that such systems have idealcharacteristics for UAVs,And the feasibility of thisalgorithm is proved by tests.

Table of content

Keywords

Publisher

AIM

Date

2019-06-03

Permanent link to this record

https://cired-repository.org/handle/20.500.12455/720
http://dx.doi.org/10.34890/942

ISSN

2032-9644

ISBN

978-2-9602415-0-1