A5090192081- Advanced SAR Imaging Techniques
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Soil Moisture and Remote Sensing
- Image and Signal Denoising Methods
- Advanced Antenna and Metasurface Technologies
- Magnetic Properties and Synthesis of Ferrites
- Optical Coherence Tomography Applications
- Electromagnetic Scattering and Analysis
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Underwater Acoustics Research
- Antenna Design and Optimization
- AI in cancer detection
- Robotics and Sensor-Based Localization
- Electromagnetic wave absorption materials
- Advanced Image Fusion Techniques
- Radar Systems and Signal Processing
- Digital Imaging for Blood Diseases
Tsinghua University
2021-2024
Jiangsu University
2022
This letter proposes a novel convolutional neural network (CNN) method for dual-polarized synthetic aperture radar (SAR) ship grained classification. The employs hybrid channel feature loss that jointly utilizes the information contained in polarized channels (VV and VH). It is demonstrated that, by adopting proposed CNN framework function, classification performance can be efficiently improved. First, instead of prevalently used threefold or fourfold division (container ship, oil tanker,...
Abstract Nowadays, polarimetric interferometric synthetic aperture radar (PolInSAR) has attracted increasing attention for the simultaneous acquisition of scattering and terrain information. The mechanism vectors corresponding to optimal coherences have shown great effect in land cover classification forest mapping. To extract vectors, different optimization algorithms are proposed but always accompanied with spatial discontinuities. This letter proposes a method optimize based on nonlocal...
Multi-band polarimetric synthetic aperture radar (PolSAR) has significant advantage in information extraction. However, the demanding acquisition requirement greatly prohibits its development. Typically, compared to low-frequency band PolSAR data, high-frequency suffers more severe data insufficiency. In this paper, authors proposed resolve issue by simulating Ka-band images from X-band images. For purpose, a conditional Generative Adversial Network (cGAN) based X-to-Ka image transfer...
Since the existing methods assume that polarization scattering matrix (PSM) of corner reflector (CR) is [1 0; 0 1], but contributions single reflection (SR), double (DR) and diffraction (SD) at different angles are ignored. In [16], we have proposed a method based on high-frequency electromagnetics to analyze PSM CR. Although cross-polarization not equal using experiments found in it cannot be explained. Therefore, this letter has deirved closed-form solutions SR DR, then strictly proves DR...
Automatic registration of multi-source remote sensing data is a challenging task due to the high non-linearity radiometric differences among various data. Feature extraction key enabling technique in algorithm design. In this letter, we prove feasibility using extracted regional features for image registration. particular, can be through pixel-level classification, and existing off-the-shelf algorithms directly adopted. Experiment results demonstrate robustness regional-feature-based method.
Data insufficiency poses a significant challenge in Ka-band Polarimetric Synthetic Aperture Radar (PolSAR) applications. Traditional PolSAR simulation approaches fail to conquer this issue due the intricate modeling and computational complexities induced by high-frequency. In paper, authors propose mitigate through neural style transfer. An X2Ka translation network is proposed transfer X-band images Ka-band. Leveraging well-verified generative Pix2Pix, adapt it accommodate specific...