With the rapid advancement in remote sensing Earth observation technology, an abundance of Time Series multispectral remote sensing Images (TSIs) from platforms like Landsat and Sentinel-2 are now accessible, offering essential data support for Time Series remote sensing images Change Detection (TSCD). However, TSCD faces misalignment challenges due to variations in radiation incidence angles, satellite orbit deviations, and other factors when capturing TSIs at the same geographic location but different times. Furthermore, another important issue that needs immediate attention is the precise determination of change moments for change areas within TSIs. To tackle these challenges, this paper proposes Multi-RLD-Net, a multi-task network that efficiently utilizes difference features to explore change areas and corresponding change moments in TSIs. To the best of our knowledge, this is the first time that using deep learning for identifying change moments in TSIs. Multi-RLD-Net integrates Optical Flow with Long Short-Term Memory (LSTM) to derive differences between TSIs. Initially, a lightweight encoder is introduced to extract multi-scale spatial features, which maximally preserve original features through a siamese structure. Subsequently, shallow spatial features extracted by the encoder are input into the novel Recursive Optical Flow Difference (ROD) module to align input features and detect differences between them, while deep spatial features extracted by the encoder are input into LSTM to capture long-term temporal dependencies and differences between hidden states. Both branches output differences among TSIs, enhancing the expressive capacity of the model. Finally, the decoder identifies change areas and their corresponding change moments using multi-task branches. Experiments on UTRNet dataset and DynamicEarthNet dataset demonstrate that proposed RLD-Net and Multi-RLD-Net outperform representative approaches, achieving F1 value improvements of 1.29% and 10.42% compared to the state-of-the art method MC2ABNet. The source code will be available soon at https://github.com/lijialu144/Multi-RLD-Net.

中文翻译：

---

有效利用差异特征：用于探索时间序列遥感图像中变化区域和变化时刻的多任务网络


随着遥感地球观测技术的快速发展，现在可以访问来自 Landsat 和 Sentinel-2 等平台的大量时间序列多光谱遥感影像 （TSI），为时间序列遥感影像变化检测 （TSCD） 提供必要的数据支持。然而，在相同地理位置但不同时间捕获 TSI 时，由于辐射入射角、卫星轨道偏差和其他因素的变化，TSCD 面临错位挑战。此外，另一个需要立即关注的重要问题是精确确定 TSI 中变化区域的变化矩。为了应对这些挑战，本文提出了 Multi-RLD-Net，这是一种多任务网络，可有效利用差异特征来探索 TSI 中的变化区域和相应的变化时刻。据我们所知，这是第一次使用深度学习来识别 TSI 中的变化时刻。Multi-RLD-Net 将 Optical Flow 与长短期记忆 （LSTM） 集成在一起，以得出 TSI 之间的差异。最初，引入轻量级编码器来提取多尺度空间特征，通过孪生结构最大限度地保留原始特征。随后，编码器提取的浅层空间特征被输入到新颖的递归光流差 （ROD） 模块中，以对齐输入特征并检测它们之间的差异，而编码器提取的深层空间特征被输入到 LSTM 中，以捕获长期的时间依赖性和隐藏状态之间的差异。这两个分支都会输出 TSI 之间的差异，从而增强模型的表达能力。最后，解码器使用多任务分支识别变化区域及其相应的变化时刻。 在 UTRNet 数据集和 DynamicEarthNet 数据集上的实验表明，所提出的 RLD-Net 和 Multi-RLD-Net 优于代表性方法，与最先进的方法 MC1ABNet 相比，F1 值提高了 1.29% 和 10.42%。源代码即将在 https://github.com/lijialu144/Multi-RLD-Net 上提供。