A Feature Fusion Network for PolSAR Image Classification Based on Physical Features and Deep Features
- 24 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Abstract
Deep learning technology has rapidly advanced in the interpretation of polarimetric synthetic aperture radar (PolSAR) images in recent years. However, deep learning methods in PolSAR image interpretation primarily rely on a significant volume of labeled data to make precise predictions, while disregarding the potential physical features of PolSAR. To solve the problem, a deep fusion network is proposed in this letter, which can effectively utilize the complementary characteristics between amplitude and physical features of PolSAR images to enhance the interpretability of the network and improve PolSAR image classification performance. In addition, an improved feature pyramid network and a learnable feature fusion module were proposed to autonomously learn the required fused feature information and avoid the process of feature selection. Finally, the spectral features of PolSAR data are fused to further enhance the discriminability of the features extracted by the proposed network, and improve the classification accuracy of the proposed method. Additionally, to verify the effectiveness of the proposed method, two real PolSAR data sets were used. The experimental results demonstrate that the proposed method achieves higher accuracy, even with a limited number of labeled samples.Keywords
Funding Information
- Scientific Research Program Funded by Shaanxi Provincial Education Department (22JK0556)
- Natural Science Foundation of Shaanxi Province (2024JCYBMS492)
This publication has 18 references indexed in Scilit:
- Self-Distillation-Based Polarimetric Image Classification with Noisy and Sparse LabelsRemote Sensing, 2023
- Multifrequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological StructureIEEE Transactions on Geoscience and Remote Sensing, 2023
- PolSAR Image Classification Based on Deep Convolutional Neural Networks Using Wavelet TransformationIEEE Geoscience and Remote Sensing Letters, 2022
- Superpixel-Based Cropland Classification of SAR Image With Statistical Texture and Polarization FeaturesIEEE Geoscience and Remote Sensing Letters, 2021
- Self-Supervised Learning for Few-Shot Image Classification2021
- Polarimetric Multipath Convolutional Neural Network for PolSAR Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2021
- Semi-Supervised PolSAR Image Classification Based on Improved Tri-Training With a Minimum Spanning TreeIEEE Transactions on Geoscience and Remote Sensing, 2020
- PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural NetworkIEEE Geoscience and Remote Sensing Letters, 2018
- PolSAR Image Classification via D-KSVD and NSCT-Domain Features ExtractionIEEE Geoscience and Remote Sensing Letters, 2016
- Four-component scattering model for polarimetric SAR image decompositionIEEE Transactions on Geoscience and Remote Sensing, 2005