Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks

TL;DR

This paper introduces a new multispectral satellite image dataset and explores convolutional neural network architectures for urban change detection, demonstrating their effectiveness on the dataset.

Contribution

It presents a new publicly available dataset for urban change detection and compares two CNN architectures using multispectral images.

Findings

Siamese and Early Fusion architectures effectively detect urban changes.

Using multiple spectral channels improves change detection accuracy.

The dataset serves as a benchmark for future research.

Abstract

The Copernicus Sentinel-2 program now provides multispectral images at a global scale with a high revisit rate. In this paper we explore the usage of convolutional neural networks for urban change detection using such multispectral images. We first present the new change detection dataset that was used for training the proposed networks, which will be openly available to serve as a benchmark. The Onera Satellite Change Detection (OSCD) dataset is composed of pairs of multispectral aerial images, and the changes were manually annotated at pixel level. We then propose two architectures to detect changes, Siamese and Early Fusion, and compare the impact of using different numbers of spectral channels as inputs. These architectures are trained from scratch using the provided dataset.