Deep Learning for the Automatic Division of Building Constructions into Sections on Remote Sensing Images

8Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

Urban areas predominantly consist of complex building structures, which are assembled of multiple building sections. From very high resolution remote sensing imagery, not only roof-tops but also the separation lines between them are visible. Since fully convolutional neural network (FCN)-based methods have become the primary choice in segmentation approaches, they have been extensively used for automatic building footprint extraction. But each of the previous works on building segmentation either lacks separation of building blocks into sections or does not produce sections of regular appearance. We propose a two-stage approach to overcome these limitations. The first step segments building and separation lines using an FCN model and the second step produces building instances by using a learning-free method. Our model receives a top-down image and a digital surface model (DSM) patch in two separate encoders. The encoder features are summed before the skip connections, which utilize the encoder features from the current and higher-resolution feature maps. We train our model with regularization losses for building shapes and separation lines on both satellite and aerial imagery. We test our model on a city that was not previously included in the training phase to show that it has the capacity to generalize across different geographical locations and architectural styles. Furthermore, we use our building section instance predictions to generate: 1) vectorized building maps and 2) a level-of-detail-1 DSM.

References Powered by Scopus

Deep residual learning for image recognition

174359Citations
50309Readers
Get full text

U-net: Convolutional networks for biomedical image segmentation

65053Citations
15534Readers

This article is free to access.

Densely connected convolutional networks

28582Citations
17051Readers
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Schuegraf, P., Zorzi, S., Fraundorfer, F., & Bittner, K. (2023). Deep Learning for the Automatic Division of Building Constructions into Sections on Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 7186–7200. https://doi.org/10.1109/JSTARS.2023.3296449

Readers over time

‘23‘2402468

Readers' Seniority

Tooltip

Lecturer / Post doc 2

50%

PhD / Post grad / Masters / Doc 2

50%

Readers' Discipline

Tooltip

Engineering 3

75%

Energy 1

25%

Article Metrics

Tooltip
Mentions
News Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free
0