POLSAR Target Recognition Using a Feature Fusion Framework Based on Monogenic Signal and Complex-Valued Nonlocal Network

Abstract

With the continuous development of synthetic aperture radar (SAR) systems, multi-polarization information has been increasingly applied to numerous fields, and automatic target recognition (ATR) in polarimetric SAR (POLSAR) has been recognized as vital problem. The SAR recognition methods can primarily fall into handcrafted feature-based algorithms and deep learning algorithms. The former exhibits excellent interpretability but insufficient generalization; the latter achieves stronger representational ability but relies on a considerable number of samples. To solve above problems, a feature fusion framework is proposed in this paper based on monogenic signal and complex-valued non-local network (CVNLNet) for POLSAR target recognition. The proposed feature fusion framework effectively uses the complementarity of handcrafted features and deep features, while making up for the disadvantages of single feature-based methods. First, a Mono-BOVW model is proposed based on monogenic signal and bag-of-visual-words (BOVW) model to extract handcrafted features, which can more fully mine the information covered in POL-SAR data in multi-scale space. Moreover, CVNLNet is built for deep feature extraction to use both the amplitude and phase covered in POLSAR data. Next, a kernel discrimination correlation analysis algorithm (KDCA) is proposed to jointly analyze and transform the two features, so as to remove redundant information while retaining effective and discriminative information. Experiments on the MSTAR dataset and the GOTCHA dataset show that the proposed framework has superior performance on single polarimetric and fully polarimetric datasets.

MF-DCMANet: A Multi-Feature Dual-Stage Cross Manifold Attention Network for PolSAR Target Recognition

“…To assess the effectiveness of the MF-DCMANet, a range of advanced PolSAR target recognition methods are compared as benchmarks, such as algorithms based on handcrafted features or deep learning and algorithms based on multi-feature fusion. Among the algorithms based on handcrafted features, we focus on comparing the methods based on monogenic features and polarization features, such as polarimetric scattering coding [56], polarimetric decomposition [57], Monogenic Scale Space (Mono) [14,58], Mono-HOG [59], Mono-BoVW [10], Monogenic Signal on Grassmann Manifolds (Mono-Grass) [15], and other methods, such as Steerable Wavelet Frames [16], Attributed scattering center (ASC) model [60]. Among deep learning-based algorithms, we compare the CNN-based and transformer-based methods, as well as the other novel methods.…”

“…Among deep learning-based algorithms, we compare the CNN-based and transformer-based methods, as well as the other novel methods. CNN-based methods include A-ConvNet [19], CV-CNN [20], CV-FCNN [61], CVNLNet [10], and RVNLNet with real input, the transformer-based method include ViT transformer [35], SpectralFormer [62], CrossViT [63], and other methods such as SymNet [64], monogenic ConvNet layer [65]. Furthermore, we also include multi-feature-based Mono-CVNLNet [10] and FEC [8] in our comparison of methods.…”

“…CNN-based methods include A-ConvNet [19], CV-CNN [20], CV-FCNN [61], CVNLNet [10], and RVNLNet with real input, the transformer-based method include ViT transformer [35], SpectralFormer [62], CrossViT [63], and other methods such as SymNet [64], monogenic ConvNet layer [65]. Furthermore, we also include multi-feature-based Mono-CVNLNet [10] and FEC [8] in our comparison of methods. The corresponding results and necessary descriptions of different methods are presented in Table 4.…”

“…A single feature only portrays the target characteristics from one aspect, which makes it difficult to describe all the information embedded in the polarization target. The application of multi-feature fusion recognition methods allows for the comprehensive exploitation and utilization of diverse information contained in multipolarization SAR data, effectively solving the problem of insufficient robustness of a single feature in complex scenarios [8][9][10]. Based on human perception and experience accumulation, researchers have designed many distinctive features from the intensity map of PolSAR targets, which generally have specific physical meanings.…”

“…The potential feature extraction process of the monogenic signal has the characteristics of rotation-invariance and scale-invariance and has been widely investigated and explored in the domain of PolSAR target recognition. Dong et al [14][15][16] and Li et al [10] introduced monogenic signal analysis into the task of SAR target recognition, systematically analyzing the advantages of monogenic signal in describing SAR target characteristics. They also designed multiple feasible classification strategies to improve the target recognition performance.…”