基于域自适应神经网络的光学与合成孔径雷达遥感图像变化检测

Change Detection of Optical and Synthetic Aperture Radar Remote Sensing Images Based on a Domain Adaptive Neural Network

为解决光学和合成孔径雷达(SAR)遥感图像变化检测中存在的原始图像特征损失和意外噪声引入问题,提高遥感影响图像变化检测质量与精度,提出一种基于域自适应神经网络的光学和SAR遥感图像变化检测方法。首先,引入域自适应约束,将提取的异构深度特征对齐到一个共同的深度特征空间中,从而提高异构图像变化检测的性能。其次,通过将对齐的深度特征输入多尺度解码器生成最终的变化图。最后,选取3个典型数据集对所提方法的有效性进行实验,并选取6种先进的检测方法进行对比分析。实验结果表明,所提检测方法在3个数据集上的平均精度、召回率、分割性能和加权值性能分别为80.81%、84.39%、73.67%和82.58%,优于对比方法。

To address the issues of original image feature loss and unexpected noise introduction in optical and synthetic aperture radar(SAR)remote sensing image change detection as well as to improve the quality and accuracy of remote sensing image change detection,a domain adaptive neural-network-based optical and SAR remote sensing image change detection method is proposed.Domain adaptive constraints were first introduced to align the extracted heterogeneous depth features to a common depth feature space,thereby improving the performance of heterogeneous image change detection.A final change map was then generated by inputting aligned depth features into the multi-scale decoder.Experiments were conducted to assess the effectiveness of the proposed method,wherein three typical datasets and six advanced detection methods were selected for comparative analysis.Experimental results show that the average accuracy,recall,segmentation performance,and weighted value performance of the proposed detection method on the three datasets are 80.81%,84.39%,73.67%,and 82.58%,respectively,which are better than those of the comparison methods.