Continental-Scale Building Detection from High Resolution Satellite Imagery

07/26/2021
by   Wojciech Sirko, et al.
6

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes. Such information can be particularly useful in developing regions where alternative data sources may be scarce. In this work, we describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery. Starting with the U-Net model, widely used in satellite image analysis, we study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance. Experiments were carried out using a dataset of 100k satellite images across Africa containing 1.75M manually labelled building instances, and further datasets for pre-training and self-training. We report novel methods for improving performance of building detection with this type of model, including the use of mixup (mAP +0.12) and self-training with soft KL loss (mAP +0.06). The resulting pipeline obtains good results even on a wide variety of challenging rural and urban contexts, and was used to create the Open Buildings dataset of 516M Africa-wide detected footprints.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 11

page 12

page 13

page 14

research
12/05/2018

Multi^3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery

We propose a novel approach for rapid segmentation of flooded buildings ...
research
06/10/2022

Fast building segmentation from satellite imagery and few local labels

Innovations in computer vision algorithms for satellite image analysis c...
research
11/29/2021

Buildings Classification using Very High Resolution Satellite Imagery

Buildings classification using satellite images is becoming more importa...
research
01/15/2023

BuildSeg: A General Framework for the Segmentation of Buildings

Building segmentation from aerial images and 3D laser scanning (LiDAR) i...
research
12/28/2022

Building Segmentation on Satellite Images and Performance of Post-Processing Methods

Researchers are doing intensive work on satellite images due to the info...
research
08/10/2023

Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone

The diversity of building architecture styles of global cities situated ...
research
05/23/2019

Workflow Design Analysis for High Resolution Satellite Image Analysis

Ecological sciences are using imagery from a variety of sources to monit...

Please sign up or login with your details

Forgot password? Click here to reset