# Deep Learning Approach for Building Detection in Satellite Multispectral Imagery

arXiv: https://arxiv.org/abs/1811.04247 · HTML: https://mlsanity.com/paper/1811.04247/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2018.

## Built on by (most cited first, 6 of 6)

- [Trinity: A No-Code AI platform for complex spatial datasets](https://mlsanity.com/paper/2106.11756/) (2021)
- [Terrain-Informed Self-Supervised Learning: Enhancing Building Footprint Extraction from LiDAR Data with Limited Annotations](https://mlsanity.com/paper/2311.01188/) (2023)
- [Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2105.05516/) (2021)
- [Automatic satellite building construction monitoring](https://mlsanity.com/paper/2209.15084/) (2022)
- [Dwelling Type Classification for Disaster Risk Assessment Using Satellite Imagery](https://mlsanity.com/paper/2211.11636/) (2022)
- [Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach](https://mlsanity.com/paper/2301.09620/) (2023)

## Abstract (arXiv)

Building detection from satellite multispectral imagery data is being a fundamental but a challenging problem mainly because it requires correct recovery of building footprints from high-resolution images. In this work, we propose a deep learning approach for building detection by applying numerous enhancements throughout the process. Initial dataset is preprocessed by 2-sigma percentile normalization. Then data preparation includes ensemble modelling where 3 models were created while incorporating OpenStreetMap data. Binary Distance Transformation (BDT) is used for improving data labeling process and the U-Net (Convolutional Networks for Biomedical Image Segmentation) is modified by adding batch normalization wrappers. Afterwards, it is explained how each component of our approach is correlated with the final detection accuracy. Finally, we compare our results with winning solutions of SpaceNet 2 competition for real satellite multispectral images of Vegas, Paris, Shanghai and Khartoum, demonstrating the importance of our solution for achieving higher building detection accuracy.