# Building Extraction at Scale using Convolutional Neural Network: Mapping of the United States

arXiv: https://arxiv.org/abs/1805.08946 · HTML: https://mlsanity.com/paper/1805.08946/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 7 of 7)

- [Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images](https://mlsanity.com/paper/2102.11262/) (2021)
- [A Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery](https://mlsanity.com/paper/2104.01263/) (2021)
- [Accurate Polygonal Mapping of Buildings in Satellite Imagery](https://mlsanity.com/paper/2208.00609/) (2022)
- [A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images-Analysis Unit,Model Scalability and Transferability](https://mlsanity.com/paper/2202.03342/) (2022)
- [An unsupervised, open-source workflow for 2D and 3D building mapping from airborne LiDAR data](https://mlsanity.com/paper/2205.14585/) (2022)
- [GeoAI at ACM SIGSPATIAL: The New Frontier of Geospatial Artificial Intelligence Research](https://mlsanity.com/paper/2210.13207/) (2022)
- [Dual skip connections in U-Net, ResUnet and U-Net3+ for remote extraction of buildings](https://mlsanity.com/paper/2303.09064/) (2023)

## Abstract (arXiv)

Establishing up-to-date large scale building maps is essential to understand urban dynamics, such as estimating population, urban planning and many other applications. Although many computer vision tasks has been successfully carried out with deep convolutional neural networks, there is a growing need to understand their large scale impact on building mapping with remote sensing imagery. Taking advantage of the scalability of CNNs and using only few areas with the abundance of building footprints, for the first time we conduct a comparative analysis of four state-of-the-art CNNs for extracting building footprints across the entire continental United States. The four CNN architectures namely: branch-out CNN, fully convolutional neural network (FCN), conditional random field as recurrent neural network (CRFasRNN), and SegNet, support semantic pixel-wise labeling and focus on capturing textural information at multi-scale. We use 1-meter resolution aerial images from National Agriculture Imagery Program (NAIP) as the test-bed, and compare the extraction results across the four methods. In addition, we propose to combine signed-distance labels with SegNet, the preferred CNN architecture identified by our extensive evaluations, to advance building extraction results to instance level. We further demonstrate the usefulness of fusing additional near IR information into the building extraction framework. Large scale experimental evaluations are conducted and reported using metrics that include: precision, recall rate, intersection over union, and the number of buildings extracted. With the improved CNN model and no requirement of further post-processing, we have generated building maps for the United States. The quality of extracted buildings and processing time demonstrated the proposed CNN-based framework fits the need of building extraction at scale.