Building Footprint Generation by Integrating Convolution Neural Network with Feature Pairwise Conditional Random Field (FPCRF)

Qingyu Li, Yilei Shi, Xin Huang, Xiao Xiang Zhu

Research output: Contribution to journalArticlepeer-review

70 Scopus citations

Abstract

Building footprint maps are vital to many remote sensing (RS) applications, such as 3-D building modeling, urban planning, and disaster management. Due to the complexity of buildings, the accurate and reliable generation of the building footprint from RS imagery is still a challenging task. In this article, an end-to-end building footprint generation approach that integrates convolution neural network (CNN) and graph model is proposed. CNN serves as the feature extractor, while the graph model can take spatial correlation into consideration. Moreover, we propose to implement the feature pairwise conditional random field (FPCRF) as a graph model to preserve sharp boundaries and fine-grained segmentation. Experiments are conducted on four different data sets: 1) Planetscope satellite imagery of the cities of Munich, Paris, Rome, and Zurich; 2) ISPRS Benchmark data from the city of Potsdam; 3) Dstl Kaggle data set; and 4) Inria Aerial Image Labeling data of Austin, Chicago, Kitsap County, Western Tyrol, and Vienna. It is found that the proposed end-to-end building footprint generation framework with the FPCRF as the graph model can further improve the accuracy of building footprint generation by using only CNN, which is the current state of the art.

Original languageEnglish
Article number9082125
Pages (from-to)7502-7519
Number of pages18
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume58
Issue number11
DOIs
StatePublished - Nov 2020
Externally publishedYes

Keywords

  • Building footprint
  • conditional random field (CRF)
  • convolution neural network (CNN)
  • graph model
  • semantic segmentation

Fingerprint

Dive into the research topics of 'Building Footprint Generation by Integrating Convolution Neural Network with Feature Pairwise Conditional Random Field (FPCRF)'. Together they form a unique fingerprint.

Cite this