SAR Image Recognition with Monogenic Scale Selection-Based Weighted Multi-task Joint Sparse Representation

Abstract

Abstract:The monogenic signal, which is defined as a linear combination of a signal and its Riesz-transformed one, provides a great opportunity for synthetic aperture radar (SAR) image recognition. However, the incredibly large number of components at different scales may result in too much of a burden for onboard computation. There is great information redundancy in monogenic signals because components at some scales are less discriminative or even have negative impact on classification. In addition, the heterogeneity of the three types of components will lower the quality of decision-making. To solve the problems above, a scale selection method, based on a weighted multi-task joint sparse representation, is proposed. A scale selection model is designed and the Fisher score is presented to measure the discriminative ability of components at each scale. The components with high Fisher scores are concatenated to three component-specific features, and an overcomplete dictionary is built. Meanwhile, the scale selection model produces the weight vector. The three component-specific features are then fed into a multi-task joint sparse representation classification framework. The final decision is made in terms of accumulated weighted reconstruction error. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset have proved the effectiveness and superiority of our method.

SAR Target Recognition via Joint Sparse and Dense Representation of Monogenic Signal

“…By sequentially solving Equations (10), (16) and 18, the shared dictionary and the class dictionary of monogenic features are acquired. The shared dictionary Φ contains more common information of the target, and the class dictionary Ψ contains more category information.…”

“…In [15], the monogenic components at different scales are united as a region covariance matrix for classification. Zhou et al [16] presented a scale selection model, where the specific monogenic component features are produced before classification. Zhou et al [17] presented the feature fusion of multi-scale monogenic components by 2D canonical correlation analysis for SAR target recognition.…”

SAR Target Recognition via Joint Sparse Representation of Monogenic Components with 2D Canonical Correlation Analysis

“…Ning et al [39] integrated the monogenic components with the polar mapping to generate a novel feature called ''monogenic polar mapping'' for SAR ATR. Zhou et al [40] conducted the selection of the multiscale monogenic components before the weighted multi-task joint sparse representation. These researches demonstrated the discrimination capability of monogenic components as for SAR target recognition.…”

“…However, the correlations between the same type of monogenic components at different scales were still not considered. Some following works [37]- [40] made some modifications to [35] and [36] but the problem was not properly considered either. So, in this study, we intend to fully consider the correlations contained in the multiscale monogenic components.…”

Fusion of Multispectral and Panchromatic Images via Spatial Weighted Neighbor Embedding

“…For instance, a new pan-sharpening method based on compressed sensing [24] is presented in [19], which employs sparse prior to regularize the degradation model and obtain competitive fusion results. Then, Li et al [20] proposed an image-fusion method based on sparse representation (SR) [25][26][27][28][29], which avoids the unavailability of HR MS images. Subsequently, SR is combined with the details injection model in [3] to further improve the quality of the fused results.…”