Building Extraction from Satellite Images Using Mask R-CNN with Building Boundary Regularization

The DeepGlobe Building Extraction Challenge poses the problem of localizing all building polygons in the given satellite images. We can create polygons using an existing instance segmentation algorithm based on Mask R-CNN. However, polygons produced from instance segmentation have irregular shapes,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhao, Kang, Kang, Jungwon, Jung, Jaewook, Sohn, Gunho
Format: Conference Proceeding
Language:English
Subjects:
Architecture
Buildings
Image segmentation
Labeling
Satellites
Training
Urban areas
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The DeepGlobe Building Extraction Challenge poses the problem of localizing all building polygons in the given satellite images. We can create polygons using an existing instance segmentation algorithm based on Mask R-CNN. However, polygons produced from instance segmentation have irregular shapes, which are far different from real building footprint boundaries and therefore cannot be directly applied to many cartographic and engineering applications. Hence, we present a method combining Mask R-CNN with building boundary regularization. Through the experiments, we find that the proposed method and Mask R-CNN achieve almost equivalent performance in terms of accuracy and completeness. However, compared to Mask R-CNN, our method produces better regularized polygons which are beneficial in many applications
ISSN:2160-7516
DOI:10.1109/CVPRW.2018.00045