L-UNet: An LSTM Network for Remote Sensing Image Change Detection
This work addresses change detection for remote sensing applications, offering an incremental improvement by enhancing spatial-temporal modeling in deep learning methods.
The authors tackled the problem of change detection in high-resolution remote sensing images by proposing L-UNet and AL-UNet, which integrate Conv-LSTM into a UNet architecture to capture spatiotemporal characteristics, resulting in improved performance over other methods on two datasets.
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.