航空学报 > 2022, Vol. 43 Issue (S1): 727239-727239   doi: 10.7527/S1000-6893.2022.27239

可见光与SAR多源遥感图像关联学习算法

王子玲, 熊振宇, 顾祥岐   

  1. 1. 海军航空大学信息融合研究所,烟台 264001
  • 收稿日期:2022-04-06 修回日期:2022-04-26 发布日期:2022-11-15
  • 通讯作者: 王子玲,E-mail:wzl001213@163.com E-mail:wzl001213@163.com
  • 基金资助:
    国家自然科学基金(61790550, 61790554)

Correlation learning algorithm of visible light and SAR cross modal remote sensing images

WANG Ziling, XIONG Zhenyu, GU Xiangqi   

  1. 1. Institute of information fusion, Naval Aviation University, Yantai 264001, China
  • Received:2022-04-06 Revised:2022-04-26 Published:2022-11-15
  • Supported by:
    National Natural Science Foundation of China (61790550, 61790554)

摘要: 针对可见光和SAR图像由于成像机理不同导致图像内容差异大,深度特征难对齐,关联速度慢,提出一种深度多源哈希网络模型实现SAR图像和可见光图像间的关联。首先,针对SAR与光学遥感图像颜色信息差异大,提出图像变换机制,将光学图像转换生成4种不同类型的光谱图像输入到网络中,打乱颜色通道,让网络更加关注于图像的纹理和轮廓信息,而对颜色信息不敏感;其次,针对SAR图像噪声大,同一场景下2种模态图像内容异构,提出图像对训练策略,减小多源图像间的特征差异;然后,针对关联效率低,存储消耗大,提出三元组哈希损失函数,提升模型的关联准确率,降低关联时间;最后,构建了一个SAR与光学双模态遥感数据集SODMRSID,实验部分验证了数据集的实用性,同时提出算法的关联准确率明显优于现有算法。

关键词: 多源异构, 遥感图像, 关联学习, 深度神经网络, 可见光图像

Abstract: Due to the different imaging mechanism of visible and SAR images, the content of images is different, the depth features are difficult to align, and the correlation speed is slow. A depth cross modal hash network model is proposed to realize the cross modal correlation between SAR images and optical images. Firstly, aiming at the great difference of color information between SAR and optical remote sensing images, an image transformation mechanism is proposed. Four different types of spectral images are generated from optical image conversion and input into the network, which disrupts the color channel, so that the network pays more attention to the texture and contour information of the image, but is not sensitive to the color information; secondly, aiming at the high noise of SAR image, two modal images in the same scene are generated. For example, the content is heterogeneous, image pair training strategy is proposed to reduce the feature difference between cross-modal images; then, aiming at the low correlation efficiency and high storage consumption, a triple hash loss function is proposed to improve the association accuracy of the model and reduce the association time. Finally, a SAR and optical dual-mode remote sensing data set is constructed. The experimental part verifies the practicability of the data set and the effectiveness of the proposed algorithm.

Key words: multi-source heterogeneous, remote sensing image, association learning, deep neural network, visible image

中图分类号: