用改进的LSTM网络提升遥感图像变化检测精度
L-UNet: An LSTM Network for Remote Sensing Image Change Detection
- 用Conv-LSTM替代UNet部分卷积层，融合时空特征
- 在两个数据集上均优于现有方法，定量与定性表现更优
- 适合需要高精度变化检测的遥感分析人员
高分辨率遥感图像的变化检测在地球观测中具有重要意义，近年来深度学习在此领域表现突出。当前主流方法基于传统卷积长短期记忆网络（Conv-LSTM），但缺乏空间特性。由于变化检测兼具时空属性，需构建端到端的时空网络。为此，本文引入扩展的Conv-LSTM结构，其具备类似卷积层的空间特征。提出L-UNet，将UNet的部分卷积层替换为Conv-LSTM；进一步提出Atrous L-UNet（AL-UNet），通过空洞结构捕获多尺度空间信息。在两个数据集上的实验表明，所提方法在数量和质量上均优于其他方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。