The impact of data volume on performance of deep learning based building rooftop extraction using very high spatial resolution aerial images

TL;DR

This study investigates how increasing data volume influences the accuracy and convergence speed of deep learning models for extracting building rooftops from very high-resolution aerial images, highlighting the importance of data size in urban mapping tasks.

Contribution

It provides a comparative analysis of deep learning architectures trained on varying dataset sizes, revealing the effects of data volume on model performance in rooftop extraction.

Findings

More training data leads to faster convergence.

Larger datasets improve extraction accuracy.

Better algorithms mitigate limited data effects.

Abstract

Building rooftop data are of importance in several urban applications and in natural disaster management. In contrast to traditional surveying and mapping, by using high spatial resolution aerial images, deep learning-based building rooftops extraction methods are efficient and accurate. Although more training data is preferred in deep learning-based tasks, the effect of data volume on building extraction models is underexplored. Therefore, the paper explores the impact of data volume on the performance of building rooftop extraction from very-high-spatial-resolution (VHSR) images using deep learning-based methods. To do so, we manually labelled 0.12m spatial resolution aerial images and perform a comparative analysis of models trained on datasets of different sizes using popular deep learning architectures for segmentation tasks, including Fully Convolutional Networks (FCN)-8s, U-Net and DeepLabv3+. The experiments showed that with more training data, algorithms converged faster and achieved higher accuracy, while better algorithms were able to better mitigate the lack of training data.