Continuous Urban Change Detection from Satellite Image Time Series with Temporal Feature Refinement and Multi-Task Integration

TL;DR

This paper introduces a novel deep learning framework for continuous urban change detection from satellite image time series, leveraging temporal feature refinement and multi-task integration to improve accuracy over existing bi-temporal and multi-temporal methods.

Contribution

The paper proposes a new framework with a temporal feature refinement module and a multi-task integration module to better capture continuous urban changes from satellite image time series.

Findings

Achieved F1 scores of 0.551, 0.440, and 0.543 on three datasets.

Outperformed existing bi-temporal and multi-temporal change detection methods.

Effectively detects continuous urban changes using high-resolution satellite data.

Abstract

Urbanization advances at unprecedented rates, leading to negative environmental and societal impacts. Remote sensing can help mitigate these effects by supporting sustainable development strategies with accurate information on urban growth. Deep learning-based methods have achieved promising urban change detection results from optical satellite image pairs using convolutional neural networks (ConvNets), transformers, and a multi-task learning setup. However, bi-temporal methods are limited for continuous urban change detection, i.e., the detection of changes in consecutive image pairs of satellite image time series (SITS), as they fail to fully exploit multi-temporal data (> 2 images). Existing multi-temporal change detection methods, on the other hand, collapse the temporal dimension, restricting their ability to capture continuous urban changes. Additionally, multi-task learning methods lack integration approaches that combine change and segmentation outputs. To address these challenges, we propose a continuous urban change detection framework incorporating two key modules. The temporal feature refinement (TFR) module employs self-attention to improve ConvNet-based multi-temporal building representations. The temporal dimension is preserved in the TFR module, enabling the detection of continuous changes. The multi-task integration (MTI) module utilizes Markov networks to find an optimal building map time series based on segmentation and dense change outputs. The proposed framework effectively identifies urban changes based on high-resolution SITS acquired by the PlanetScope constellation (F1 score 0.551), Gaofen-2 (F1 score 0.440), and WorldView-2 (F1 score 0.543). Moreover, our experiments on three challenging datasets demonstrate the effectiveness of the proposed framework compared to bi-temporal and multi-temporal urban change detection and segmentation methods.