arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.03378cs.CV
收藏

用于 PolSAR 图像分类的黎曼复矩阵卷积网络

Riemannian Complex Matrix Convolution Network for PolSAR Image Classification

Shaanxi Key Laboratory for Network Computing and Security Technology(陕西省网络计算与安全技术重点实验室);Department of Computer Science and Technology(计算机科学与技术学院)

Junfei Shi, Wei Wang, Haiyan Jin, Mengmeng Nie, Shanshan Ji

AI总结:

针对 PolSAR 协方差复矩阵结构难以直接建模的问题,提出黎曼复矩阵卷积网络,定义黎曼卷积等运算并结合 CNN 与快速核学习,在三组真实数据上取得优于现有方法的分类效果。

摘要:

近年来,深度学习方法在极化合成孔径雷达(Polarimetric Synthetic Aperture Radar,PolSAR)图像分类中取得了优异性能。现有深度学习方法通过将协方差矩阵转换为特征向量或复值向量作为输入来学习 PolSAR 数据。然而,这些方法都无法直接学习复矩阵的结构,并破坏了通道相关性。为学习复矩阵的几何结构,我们首次在黎曼空间中提出用于 PolSAR 图像分类的黎曼复矩阵卷积网络,该网络直接利用复矩阵作为网络输入,并定义黎曼运算来学习复矩阵特征。所提出的黎曼复矩阵卷积网络将 PolSAR 复矩阵视为赋予在黎曼流形上的对象,并在黎曼空间中定义了一系列新的黎曼卷积、ReLu 和 LogEig 运算,突破了传统网络的欧几里得约束。随后,附加一个 CNN 模块以增强上下文黎曼特征。此外,还为所提方法开发了一种快速核学习方法,用于学习类别特定特征并有效减少计算时间。实验在三组具有不同波段和传感器的真实 PolSAR 数据上进行。实验结果表明,与最先进方法相比,所提方法能够获得更优性能。

英文摘要:

Recently, deep learning methods have achieved superior performance for Polarimetric Synthetic Aperture Radar(PolSAR) image classification. Existing deep learning methods learn PolSAR data by converting the covariance matrix into a feature vector or complex-valued vector as the input. However, all these methods cannot learn the structure of complex matrix directly and destroy the channel correlation. To learn geometric structure of complex matrix, we propose a Riemannian complex matrix convolution network for PolSAR image classification in Riemannian space for the first time, which directly utilizes the complex matrix as the network input and defines the Riemannian operations to learn complex matrix's features. The proposed Riemannian complex matrix convolution network considers PolSAR complex matrix endowed in Riemannian manifold, and defines a series of new Riemannian convolution, ReLu and LogEig operations in Riemannian space, which breaks through the Euclidean constraint of conventional networks. Then, a CNN module is appended to enhance contextual Riemannian features. Besides, a fast kernel learning method is developed for the proposed method to learn class-specific features and reduce the computation time effectively. Experiments are conducted on three sets of real PolSAR data with different bands and sensors. Experiments results demonstrates the proposed method can obtain superior performance than the state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑