study on polsar target detection essentially requires the cattering information and polarimetric statistical data. theoretical analysis shows that some terms of the second order scattering matrices such as coherence and covariance matrix clearly show the differences between nonsymmetrical man-made objects and natural clatters which being reflection symmetric. using the model derived from these ...

Reliable and timely rice distribution information is of great value for real-time, quantitative, localized control production information. Synthetic aperture radar (SAR) has all-weather all-day observation capability to monitor in tropical subtropical areas. To improve the physical interpretability spatial deep learning model SAR field extraction, a new SHapley Additive exPlanation (SHAP) value...

The present study introduces the four-component scattering power decomposition (4-CSPD) algorithm with rotation of covariance matrix, and presents an experimental proof of the equivalence between the 4-CSPD algorithms based on rotation of covariance matrix and coherency matrix. From a theoretical point of view, the 4-CSPD algorithms with rotation of the two matrices are identical. Although it s...

Polarimetric synthetic aperture radar (PolSAR) image classification has been investigated vigorously in various remote sensing applications. However, it is still a challenging task nowadays. One significant barrier lies the speckle effect embedded PolSAR imaging process, which greatly degrades quality of images and further complicates classification. To this end, we present novel method that re...

Observation of the global environment by microwave remote sensing technology has been attracting attention recently. Image classification is one of the important applications in POLSAR (Polarimetric SAR) image analysis. Various techniques are proposed. The scattering model decomposition [1] is one of the powerful techniques among them. This technique decomposes a covariance matrix derived by th...

Deep neural networks (DNNs) appear to be a solution for the classification of polarimetric synthetic aperture radar (PolSAR) data in that they outperform classical supervised classifiers under condition sufficient training samples. The design classifier is challenging because DNNs can easily overfit due limited remote sensing samples and unavoidable noisy labels. In this article, softmax loss s...

Urban extraction is one of the most expected applications using remote sensing, but the automatic extraction has been challenging. Especially in the field of SAR applications, the complex scattering in the urban area is sensitive to the building spatial arrangement, and it prevents from the automatic extraction. Spaceborne Polarimetric synthetic aperture radar (POLSAR), an advanced approach to ...

The timely detection and mapping of surface water bodies from Polarimetric Synthetic Aperture Radar (PolSAR) images are great significance for emergency management post-disaster restoration tasks. Though various methods have been proposed in previous years, there still some inherent flaws. Thus, this paper proposes a new extraction method based on superpixels Graph Convolutional Networks (GCN)....

The model-based polarimetric decomposition is extensively studied due to its simplicity and clear physical interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) data. Though there are many fine basic scattering models well-designed methods, the overestimation volume (OVS) may still occur in highly oriented buildings, resulting severe mechanism ambiguity. It well known that not only v...