Remote Sensing Data Preparation for Recognition and Classification of Building Roofs

Emil Hristov (), Dessislava Petrova-Antonova (), Aleksandar Petrov, Milena Borukova and Evgeny Shirinyan
Additional contact information
Emil Hristov: GATE Institute, Sofia University “St. Kliment Ohridski”, 1504 Sofia, Bulgaria
Dessislava Petrova-Antonova: GATE Institute, Sofia University “St. Kliment Ohridski”, 1504 Sofia, Bulgaria
Aleksandar Petrov: GATE Institute, Sofia University “St. Kliment Ohridski”, 1504 Sofia, Bulgaria
Milena Borukova: GATE Institute, Sofia University “St. Kliment Ohridski”, 1504 Sofia, Bulgaria
Evgeny Shirinyan: GATE Institute, Sofia University “St. Kliment Ohridski”, 1504 Sofia, Bulgaria

Data, 2023, vol. 8, issue 5, 1-19

Abstract: Buildings are among the most significant urban infrastructure that directly affects citizens’ livelihood. Knowledge about their rooftops is essential not only for implementing different Levels of Detail (LoD) in 3D city models but also for performing urban analyses related to usage potential (solar, green, social), construction assessment, maintenance, etc. At the same time, the more detailed information we have about the urban environment, the more adequate urban digital twins we can create. This paper proposes an approach for dataset preparation using an orthophoto with a resolution of 10 cm. The goal is to obtain roof images into separate GeoTIFFs categorised by type (flat, pitched, complex) in a way suitable for feeding rooftop classification models. Although the dataset is initially elaborated for rooftop classification, it can be applied to developing other deep-learning models related to roof recognition, segmentation, and usage potential estimation. The dataset consists of 3617 roofs covering the Lozenets district of Sofia, Bulgaria. During its preparation, the local-specific context is considered.

Keywords: building rooftop classification; roof dataset preparation; orthophoto processing (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: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2306-5729/8/5/80/pdf (application/pdf)
https://www.mdpi.com/2306-5729/8/5/80/ (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:5:p:80-:d:1135919

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 ().