Autonomous monitoring system for the detection of disrupting power cables on distribution networks using computer vision techniques
Paper number
2133Conference name
CIRED 2019Conference date
3-6 June 2019Conference location
Madrid, SpainPeer-reviewed
YesMetadata
Show full item recordAuthors
Del Hoyo, Ignacio Leonardo, UTFPR, BrazilBianchi Filho, José Francisco, Lactec, Brazil
Alcantara Andrade, Gerson , Copel, Brazil
Cordeiro Vogt, Guilherme , UFPR, Brazil
Murmel, Yan Victor, UTFPR, Brazil
Ribeiro Júnior, Sebastião, UFPR, Brazil
Naoto Tabata, Alan , Lactec, Brazil
dos Santos Haveroth, Gabriel , Lactec, Brazil
Abstract
This paper aims on evaluating classical computer vision techniques in order to detect whether electric cables are falling to the ground or not. A proprietary dataset containing several simulation cases was built with the Unreal Engine 4 framework and simulations were performed on MATLAB with an algorithm that performs frame subtraction and applies filters in order to detect movement on images. Evaluated metrics were precision, recall, F1 score and Frames Per Second (FPS) processed. The algorithm performed satisfactorily on most cases, being able to achieve a precision of up to 100.00%, 26.67% recall, 0.4058 F1 score and up to11 FPS.Publisher
AIMDate
2019-06-03Published in
Permanent link to this record
https://cired-repository.org/handle/20.500.12455/745http://dx.doi.org/10.34890/966