当前位置: X-MOL 学术IEEE Trans. Geosci. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Bipartite Graph Attention Autoencoders for Unsupervised Change Detection Using VHR Remote Sensing Images
IEEE Transactions on Geoscience and Remote Sensing ( IF 8.2 ) Pub Date : 2022-07-13 , DOI: 10.1109/tgrs.2022.3190504
Meng Jia 1 , Cheng Zhang 1 , Zhiqiang Zhao 1 , Lei Wang 1
Affiliation  

Detecting land cover change is an essential task in very-high-spatial-resolution (VHR) remote sensing applications. However, because VHR images can capture the details of ground objects, the scenes of VHR images are usually complex. For example, VHR images usually show distinct appearances or features of the same object, aroused by noise, climate conditions, imaging angles, etc. To address this issue, this article proposes a novel unsupervised approach named bipartite graph attention autoencoders (BGAAEs) for VHR image change detection. BGAAE, a further improved way of using dual convolutional autoencoders based on the architecture of image translation, equips the encoder layers with a graph attention mechanism (GAM). To generate an effective difference image, it consists of two additional loss terms: the domain correlation and semantic consistency losses, in addition to the reconstruction loss. The domain correlation loss is designed based on the encoder layers, aiming to enforce the spatial alignment of deep feature representations of the unchanged objects and mitigate the influence of pixel changes on the learning objective. The semantic consistency loss focuses on ensuring the semantic feature consistency of the bitemporal images after transcoding and allows for more flexible transformations. The experimental results on four VHR image datasets demonstrate the superiority of the proposed method.

中文翻译:

使用 VHR 遥感图像进行无监督变化检测的二分图注意自动编码器

检测土地覆盖变化是超高空间分辨率 (VHR) 遥感应用中的一项重要任务。但是,由于 VHR 图像可以捕捉到地面物体的细节,因此 VHR 图像的场景通常比较复杂。例如,VHR 图像通常显示同一物体的不同外观或特征,由噪声、气候条件、成像角度等引起。为了解决这个问题,本文提出了一种新的无监督方法,称为用于 VHR 的二部图注意力自动编码器 (BGAAE)图像变化检测。BGAAE 是一种使用基于图像转换架构的双卷积自动编码器的进一步改进方法,它为编码器层配备了图形注意机制 (GAM)。为了生成有效的差异图像,它包含两个额外的损失项:除了重建损失之外,域相关性和语义一致性损失。域相关损失是基于编码器层设计的,旨在强制未更改对象的深度特征表示的空间对齐,并减轻像素变化对学习目标的影响。语义一致性损失侧重于确保转码后双时相图像的语义特征一致性,并允许更灵活的转换。在四个 VHR 图像数据集上的实验结果证明了该方法的优越性。旨在强制未更改对象的深度特征表示的空间对齐,并减轻像素变化对学习目标的影响。语义一致性损失侧重于确保转码后双时相图像的语义特征一致性,并允许更灵活的转换。在四个 VHR 图像数据集上的实验结果证明了该方法的优越性。旨在强制未更改对象的深度特征表示的空间对齐,并减轻像素变化对学习目标的影响。语义一致性损失侧重于确保转码后双时相图像的语义特征一致性,并允许更灵活的转换。在四个 VHR 图像数据集上的实验结果证明了该方法的优越性。
更新日期:2022-07-13
down
wechat
bug