Analysis Feature Extraction for SAR Data Classification
For polarimetric synthetic aperture radar (PolSAR) data, various polarimetric signatures can be obtained by target decomposition techniques, which are of great help for characterizing the land cover. It is straightforward to combine these polarimetric features together and formulate them as a third-order polarimetric feature tensor. However, how to make full use of the abundant information provided by these polarimetric features remains a challenge. A feasible solution is applying feature extraction (FE) techniques on the high-dimensional polarimetric manifold to obtain a lower dimensional intrinsic feature set. Common FE methods, such as principal component analysis (PCA), independent component analysis (ICA), etc., use matrix linear algebra and require rearranging the original tensor into a matrix. This leads to the loss of the spatial information of the PolSAR data. In this paper, to jointly take advantage of the spatial and feature information, a novel FE scheme incorporating ICA with the tensor decomposition techniques is proposed.
After applying the proposed FE method on the third-order polarimetric feature tensor, each PolSAR image pixel is represented by a low-dimensional intrinsic feature vector. Furthermore, these feature vectors are fed to the k-nearest neighbor (KNN) classifier and support-vector-machine classifier for supervised classification. Simulated data, together with two measured data sets, i.e., Flevoland of Airborne Synthetic Aperture Radar (AIRSAR) and Québec City of Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR), are utilized to evaluate the performance of the proposed method. For comparison purpose, several classical and advanced FE methods, such as PCA, ICA, Laplacian eigenmaps, and LRTAdr – (K1,K2,p), are also applied. The experimental results demonstrate the superiority of the proposed FE method in three folds: 1) The extracted features by the proposed method are more discriminative- characterized by the high separability in the scatterplots; 2) the classification accuracy is improved as much as approximately 7% compared with the complex Wishart classifier; and 3) the proposed method is computational efficient and has fast convergence.
Related Matlab Project Titles:
- Hyperspectral Band Selection by Multitask Sparsity Pursuit.
- When Pixels Team up: Spatially Weighted Sparse Coding for Hyperspectral Image Classification.
- Hierarchical Unsupervised Change Detection in Multitemporal Hyperspectral Images.
- A Geometric Unmixing Concept for the Selection of Optimal Binary Endmember Combinations.
- Combining Ordered Subsets and Momentum for Accelerated X-Ray CT Image Reconstruction.
- Spectral Image Unmixing From Optimal Coded-Aperture Compressive Measurements.
- Automatic Spatial–Spectral Feature Selection for Hyperspectral Image via Discriminative Sparse Multimodal Learning.
- Collaborative Representation for Hyperspectral Anomaly Detection.
- Automatic Recognition of Isolated Buildings on Single-Aspect SAR Image Using Range Detector.
- Wavelet-Based Texture Features for the Classification of Age Classes in a Maritime Pine Forest.
- Target Recognition in SAR Images via Classification on Riemannian Manifolds.
- Three-Dimensional Object Matching in Mobile Laser Scanning Point Clouds.
- Intensity-Based Visual Servoing for Instrument and Tissue Tracking in 3D Ultrasound Volumes.
- Class-Dependent Sparse Representation Classifier for Robust Hyperspectral Image Classification.
- The Gridding Method for Image Reconstruction of Nonuniform Aperture Synthesis Radiometers.
- Compressed Sensing MRI via Two-stage Reconstruction.
- Weakly Supervised Learning for Target Detection in Remote Sensing Images.
- Exploring Robust Diagnostic Signatures for Cutaneous Melanoma Utilizing Genetic and Imaging Data.
- Smartphone-Based Wound Assessment System for Patients With Diabetes.
We want to support Uncompromise Matlab service for all your Requirements Our Reseachers and Technical team keep update the technology for all subjects ,We assure We Meet out Your Needs.
- Matlab Research Paper Help
- Matlab assignment help
- Matlab Project Help
- Matlab Homework Help
- Simulink assignment help
- Simulink Project Help
- Simulink Homework Help
- Matlab Research Paper Help
- NS3 Research Paper Help
- Omnet++ Research Paper Help
- Customised Matlab Assignments
- Global Assignment Knowledge
- Best Assignment Writers
- Certified Matlab Trainers
- Experienced Matlab Developers
- Over 400k+ Satisfied Students
- Ontime support
- Best Price Guarantee
- Plagiarism Free Work
- Correct Citations
Unlimited support we offer you
For better understanding purpose we provide following Materials for all Kind of Research & Assignment & Homework service.
- Result snapshot
- Video Tutorial
- Instructions Profile
- Sofware Install Guide
- Execution Guidance
- Implement Plan
Matlab projects innovators has laid our steps in all dimension related to math works.Our concern support matlab projects for more than 10 years.Many Research scholars are benefited by our matlab projects service.We are trusted institution who supplies matlab projects for many universities and colleges.
Reasons to choose Matlab Projects .org???
Our Service are widely utilized by Research centers.More than 5000+ Projects & Thesis has been provided by us to Students & Research Scholars. All current mathworks software versions are being updated by us.
Our concern has provided the required solution for all the above mention technical problems required by clients with best Customer Support.
- Novel Idea
- Ontime Delivery
- Best Prices
- Unique Work