A Semantically Annotated 15-Class Ground Truth Dataset for Substation Equipment to Train Semantic Segmentation Models

Andreas Anael Pereira Gomes (), Francisco Itamarati Secolo Ganacim, Fabiano Gustavo Silveira Magrin, Nara Bobko, Leonardo Göbel Fernandes, Anselmo Pombeiro and Eduardo Félix Ribeiro Romaneli
Additional contact information
Andreas Anael Pereira Gomes: Graduate Program in Energy Systems, Universidade Tecnológica Federal do Paraná (UTFPR), 3165 Sete de Setembro Ave, Curitiba 80230-901, PR, Brazil
Francisco Itamarati Secolo Ganacim: Tecgraf Institute of Technical-Scientific Software Development of PUC-Rio, Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio), 225 Marquês de São Vicente St, Building Pe. Belisário Velloso, Rio de Janeiro 22453-900, RJ, Brazil
Fabiano Gustavo Silveira Magrin: Graduate Program in Energy Systems, Universidade Tecnológica Federal do Paraná (UTFPR), 3165 Sete de Setembro Ave, Curitiba 80230-901, PR, Brazil
Nara Bobko: Professional Master’s Degree in Mathematics in National Network, Universidade Tecnológica Federal do Paraná (UTFPR), 3165 Sete de Setembro Ave, Curitiba 80230-901, PR, Brazil
Leonardo Göbel Fernandes: Graduate Program in Electrical and Computer Engineering, Universidade Tecnológica Federal do Paraná (UTFPR), 3165 Sete de Setembro Ave, Curitiba 80230-901, PR, Brazil
Anselmo Pombeiro: Operation and Maintenance Engineering Superintendence, Copel, 158 José Izidoro Biazetto St, Curitiba 81200-240, PR, Brazil
Eduardo Félix Ribeiro Romaneli: Graduate Program in Energy Systems, Universidade Tecnológica Federal do Paraná (UTFPR), 3165 Sete de Setembro Ave, Curitiba 80230-901, PR, Brazil

Data, 2023, vol. 8, issue 7, 1-16

Abstract: The lack of annotated semantic segmentation datasets for electrical substations in the literature poses a significant problem for machine learning tasks; before training a model, a dataset is needed. This paper presents a new dataset of electric substations with 1660 images annotated with 15 classes, including insulators, disconnect switches, transformers and other equipment commonly found in substation environments. The images were captured using a combination of human, fixed and AGV-mounted cameras at different times of the day, providing a diverse set of training and testing data for algorithm development. In total, 50,705 annotations were created by a team of experienced annotators, using a standardized process to ensure accuracy across the dataset. The resulting dataset provides a valuable resource for researchers and practitioners working in the fields of substation automation, substation monitoring and computer vision. Its availability has the potential to advance the state of the art in this important area.

Keywords: semantic segmentation; annotation; labeling; automated methods; substation automation; machine learning; weak supervision; computer vision; artificial intelligence; image dataset (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/8/7/118/pdf (application/pdf)
https://www.mdpi.com/2306-5729/8/7/118/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:8:y:2023:i:7:p:118-:d:1187168

Access Statistics for this article

Data is currently edited by Ms. Cecilia Yang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().