L-UNet: An LSTM Network for Remote Sensing Image Change Detection

TL;DR

L-UNet introduces an end-to-end spatiotemporal deep learning model using LSTM and UNet architectures for improved change detection in high-resolution remote sensing images, capturing both spatial and temporal features.

Contribution

The paper proposes L-UNet and Atrous L-UNet, novel deep learning models that integrate Conv-LSTM with UNet and Atrous structures for enhanced change detection.

Findings

Outperforms existing methods in accuracy and quality

Effective in capturing multiscale spatial information

Demonstrates advantages on multiple datasets

Abstract

Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.