What is it about?

The paper proposes an effective and automated method of building extraction under the constraint of elevation contour lines from high resolution remote sensing images.

Featured Image

Why is it important?

Extraction of building information from high resolution remote sensing images has become a research hotspot

Perspectives

In this paper, an effective and highly automated method of building extraction, which can distinguish the top of a building from the elevation under the constraint of elevation contour lines, from a monocular optical high resolution image is proposed. Compared with the method of using shadows as auxiliary information, the elevation contours of the building can not only accurately locate the building, but also better reflect the relationship between the building roof and elevation. Moreover, image segmentation with Grab-Cut can better preserve the entire building boundary.

Dr Ka Zhang
Nanjing Normal University

Read the Original

This page is a summary of: Building Extraction from High-Resolution Remote Sensing Images Based on GrabCut with Automatic Selection of Foreground and Background Samples, Photogrammetric Engineering & Remote Sensing, April 2020, American Society for Photogrammetry and Remote Sensing,
DOI: 10.14358/pers.86.4.235.
You can read the full text:

Read

Contributors

The following have contributed to this page