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.
Abstract (translated)
高分辨率遥感图像变化检测是地球观测中的重要任务，已被广泛研究。近年来，深度学习在众多遥感任务中展现出显著成效。当前基于深度学习的变化检测方法主要依赖于传统的长短期记忆网络（Conv-LSTM），该方法缺乏空间特征。由于变化检测是一个兼具空间性与时域性的过程，因此有必要提出一种端到端的时空网络。为实现这一目标，引入了Conv-LSTM结构扩展。鉴于其与卷积层具有相似的空间特性，提出了L-UNet（将UNet中的部分卷积层替换为Conv-LSTM）以及进一步采用空洞结构以获取多尺度空间信息的AL-UNet（Atrous L-UNet）。在两个数据集上进行的实验表明，所提方法在定量与定性评估中均优于其他部分方法。
URL
https://arxiv.org/abs/2603.22842
