Use of a DNN-Based Image Translator with Edge Enhancement Technique to Estimate Correspondence between SAR and Optical Images
Use of a DNN-Based Image Translator with Edge Enhancement Technique to Estimate Correspondence between SAR and Optical Images
复制标题
DOI：
10.3390/app12094159
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
H. Toriya;Ashraf Dewan;H. Ikeda;Narihiro Owada;Mahdi Saadat;Fumiaki Inagaki;Y. Kawamura;I. Kitahara
中科院分区：
文献类型：
--
作者：
H. Toriya;Ashraf Dewan;H. Ikeda;Narihiro Owada;Mahdi Saadat;Fumiaki Inagaki;Y. Kawamura;I. Kitahara
提出了一种基于图像特征的关键点匹配算法，实现了合成孔径雷达(SAR)图像与光学图像的局部对应。为了实现准确的匹配，在相应的位置获取共同的图像特征。由于合成孔径雷达图像和光学图像的外观不同，很难找到相似的特征来解释几何校正。在这项工作中，利用深度神经网络(DNN)构建图像翻译器，并利用边缘增强的条件生成对抗网络(CGAN)进行训练，以找到SAR图像和光学图像之间的对应位置。当使用传统的cGAN时，在转换的图像中会出现许多模糊，它们降低了关键点匹配的精度。为此，提出了一种在cGANS结构中应用边缘增强滤波器来寻找SAR图像和光学图像之间的对应点的新方法，以准确地配准来自不同传感器的图像。结果表明，该方法能够较准确地估计合成孔径雷达图像与光学图像之间的对应点。
In this paper, the local correspondence between synthetic aperture radar (SAR) images and optical images is proposed using an image feature-based keypoint-matching algorithm. To achieve accurate matching, common image features were obtained at the corresponding locations. Since the appearance of SAR and optical images is different, it was difficult to find similar features to account for geometric corrections. In this work, an image translator, which was built with a DNN (deep neural network) and trained by conditional generative adversarial networks (cGANs) with edge enhancement, was employed to find the corresponding locations between SAR and optical images. When using conventional cGANs, many blurs appear in the translated images and they degrade keypoint-matching accuracy. Therefore, a novel method applying an edge enhancement filter in the cGANs structure was proposed to find the corresponding points between SAR and optical images to accurately register images from different sensors. The results suggested that the proposed method could accurately estimate the corresponding points between SAR and optical images.