Deep convolutional neural network application on rooftop detection for aerial image

TL;DR

This paper presents a CNN-based method for automatic rooftop detection in aerial images, focusing on post-earthquake building identification to aid reconstruction efforts.

Contribution

It introduces a novel CNN application tailored for small detached house detection in aerial imagery, with hyperparameter tuning for improved accuracy.

Findings

Effective building detection and segmentation demonstrated

High accuracy in identifying small detached houses

Competitive performance compared to existing methods

Abstract

As one of the most destructive disasters in the world, earthquake causes death, injuries, destruction and enormous damage to the affected area. It is significant to detect buildings after an earthquake in response to reconstruction and damage evaluation. In this research, we proposed an automatic rooftop detection method based on the convolutional neural network (CNN) to extract buildings in the city of Christchurch and tuned hyperparameters to detect small detached houses from the aerial image. The experiment result shows that our approach can effectively and accurately detect and segment buildings and has competitive performance.