Change detection in remote sensing images aims to accurately determine any significant land surface changes based on acquired multi-temporal image data, being a pivotal task of remote sensing image processing. Over the past few years, owing to its powerful learning and expression ability, deep learning has been widely applied in the general field of image processing and has demonstrated remarkable potentials in performing change detection in images. However, a majority of the existing deep learning-based change detection mechanisms are modified from single-image semantic segmentation algorithms, without considering the temporal information contained within the images, thereby not always appropriate for real-world change detection. This paper proposes a High-Resolution Triplet Network (HRTNet) framework, including a dynamic inception module, to tackle such shortcomings in change detection. First, a novel triplet input network is introduced, which is capable of learning bi-temporal image features, extracting the temporal information reflecting the difference between images over time. Then, a network is employed to extract high-resolution image features, ensuring the learned features preserving high-resolution characteristics with minimal reduction of information. The paper also proposes a novel dynamic inception module, which helps improve the feature expression ability of HRTNet, enriching the multi-scale information of the features extracted. Finally, the distances between feature pairs are measured to generate a high-precision change map. The effectiveness and robustness of HRTNet are verified on three popular high-resolution remote sensing image datasets. Systematic experimental results show that the proposed approach outperforms state-of-the-art change detection methods.

遥感图像中的变化检测旨在基于获取的多时相图像数据准确确定任何重要的陆地表面变化，这是遥感图像处理的关键任务。在过去的几年中，由于其强大的学习和表达能力，深度学习已广泛应用于图像处理的一般领域，并显示出在进行图像变化检测方面的巨大潜力。但是，大多数现有的基于深度学习的更改检测机制都是通过单图像语义分割算法进行修改的，而没有考虑图像中包含的时间信息，因此并不总是适合于现实世界中的更改检测。本文提出了一个高分辨率三重态网络（HRTNet）框架，其中包括一个动态启动模块，解决变更检测中的此类缺陷。首先，引入了一种新颖的三重态输入网络，该网络能够学习双时态图像特征，提取反映时间之间图像差异的时态信息。然后，采用网络来提取高分辨率图像特征，以最小的信息减少量确保学习到的特征保留高分辨率特征。本文还提出了一种新颖的动态启动模块，该模块有助于提高HRTNet的特征表达能力，丰富提取的特征的多尺度信息。最后，测量特征对之间的距离以生成高精度的变化图。在三个流行的高分辨率遥感影像数据集上验证了HRTNet的有效性和鲁棒性。