Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data

TL;DR

This paper introduces a deep learning framework combining convolutional and recurrent neural networks to improve urban change detection using multitemporal Sentinel-2 satellite data, achieving high accuracy and enhanced change classification.

Contribution

It presents a novel deep learning approach integrating CNNs and LSTMs for more effective urban change detection from multitemporal satellite imagery.

Findings

Overall accuracy exceeds 95% on the OSCD dataset.

LSTM-based models improve change detection F1 score by 1.5%.

Additional temporal images enhance detection performance.

Abstract

\begin{abstract} The advent of multitemporal high resolution data, like the Copernicus Sentinel-2, has enhanced significantly the potential of monitoring the earth's surface and environmental dynamics. In this paper, we present a novel deep learning framework for urban change detection which combines state-of-the-art fully convolutional networks (similar to U-Net) for feature representation and powerful recurrent networks (such as LSTMs) for temporal modeling. We report our results on the recently publicly available bi-temporal Onera Satellite Change Detection (OSCD) Sentinel-2 dataset, enhancing the temporal information with additional images of the same region on different dates. Moreover, we evaluate the performance of the recurrent networks as well as the use of the additional dates on the unseen test-set using an ensemble cross-validation strategy. All the developed models during the validation phase have scored an overall accuracy of more than 95%, while the use of LSTMs and further temporal information, boost the F1 rate of the change class by an additional 1.5%.