双边对抗自编码网络的无监督异质遥感图像变化检测  

Bipartite adversarial autoencoder network for unsupervised detection of changes in heterogeneous remote sensing images

作　　者：贾萌 赵秦 鲁晓锋[1] Jia Meng;Zhao Qin;Lu Xiaofeng(School of Computer Science and Engineering,Xi’an University of Technology,Xi’an 710048,China)

机构地区：[1]西安理工大学计算机科学与工程学院,西安710048

出　　处：《中国图象图形学报》2024年第8期2188-2204,共17页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62076201);陕西省重点研发计划资助(2023-YBGY-222);碑林区科技计划项目(GX2246)。

摘　　要：目的异质遥感图像由不同类型的传感器所获取,在数据结构、分辨率及辐射特性上均存在巨大差异。变化检测任务旨在通过分析在不同时间获取的同一目标区域的图像来检测地表覆盖物变化,然而异质遥感图像的数据异构特性会使得变化检测过程更加困难。针对这个问题,提出了一种嵌入聚类分析的双边对抗自编码网络来实现异质遥感图像地物变化的精确检测。方法构造双边对抗自编码网络对异质遥感图像进行重构和风格转换,通过结构一致性损失和对抗损失对网络训练进行约束,迫使网络将异质图像转换到公共数据域。考虑到变化区域像素对于对抗损失函数在网络优化中的不利影响,对映射到公共数据域的两对同质图像进行聚类分析,基于此提出一种新的语义信息约束的对抗损失函数,迫使网络生成具有更加一致风格的图像。结果在4组典型的异质遥感图像数据集上对提出的变化检测网络性能进行测试,在Italy数据集、California数据集、Tianhe数据集以及Shuguang数据集上的总体检测精度分别达到0.9705、0.9382、0.9947以及0.9826。与现有的传统以及深度学习方法对比,提出算法在视觉及定量分析结果上均取得了较好的检测性能。结论针对异质遥感图像变化检测所要面临的由环境、数据异构等因素造成的检测困难、错检率高的问题,提出的基于双边对抗自编码网络的无监督异质遥感图像变化检测方法,既可以实现变化检测过程完全无监督,又充分利用网络特性和语义信息,提高了变化检测性能。Objective Heterogeneous remote sensing images from different sensors are quite different in imaging mecha⁃nism,radiation characteristics,and geometric characteristics.Thus,they reflect the physical properties of the ground tar⁃get at different levels.Therefore,no relationship exists between the observed values of the same object,which usually leads to“pseudo changes”.As a result,the change detection task has more difficulty obtaining accurate change informa⁃tion of the observed ground objects.Efforts have been made toward unsupervised detection of changes in heterogeneous remote sensing images by designing various methods to obtain change information.However,traditional image difference operators based on the difference or ratio of radiation measurement is no longer applicable.Therefore,transferring the bitemporal images in a common space is a convenient way to calculate differences.Considering the excellent and flexible feature learning capability of deep neural networks,they have been widely applied in change detection tasks for heteroge⁃neous images to effectively alleviate the influence of“pseudo changes”.Moreover,by fully utilizing the characteristics of deep neural networks,they can be designed to transform heterogeneous remote sensing images into the same feature domain.Then,the change information can be accurately represented.Inspired by the paradigm of image translation,het⁃erogeneous images are transformed into a common domain with consistent feature representations to enable direct compari⁃sons of data.The key point of this task is learning a suitable one-to-one mapping to build a relationship between distinct appearances of images and exclude the effect of interference factors.Therefore,this study proposes a bipartite adversarial autoencoder network with clustering(BAACL)to detect changes between heterogeneous remote sensing images.Method A bipartite adversarial autoencoder network is constructed to reconstruct the bitemporal images and achieve the transformation of heterogeneous i

关 键 词：域转换 聚类分析 语义信息 无监督变化检测 异质遥感图像 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]