scholarly journals Sparsity Based Full Rank Polarimetric Reconstruction of Coherence Matrix T

2019 ◽  
Vol 11 (11) ◽  
pp. 1288 ◽  
Author(s):  
Hossein Aghababaee ◽  
Giampaolo Ferraioli ◽  
Laurent Ferro-Famil ◽  
Gilda Schirinzi ◽  
Yue Huang
Keyword(s):  
Super Resolution ◽  
Full Rank ◽  
Real Data ◽  
Natural Environments ◽  
Data Sets ◽  
Scattering Pattern ◽  
Component Decomposition ◽  
Resolution Imaging ◽  
Processing Techniques ◽  
Physical Features

In the frame of polarimetric synthetic aperture radar (SAR) tomography, full-ranks reconstruction framework has been recognized as a significant technique for fully characterization of superimposed scatterers in a resolution cell. The technique, mainly is characterized by the advantages of polarimetric scattering pattern reconstruction, allows physical feature extraction of the scatterers. In this paper, to overcome the limitations of conventional full-rank tomographic techniques in natural environments, a polarimetric estimator with advantages of super-resolution imaging is proposed. Under the frame of compressive sensing (CS) and sparsity based reconstruction, the profile of second order polarimetric coherence matrix T is recovered. Once the polarimetric coherence matrices of the scatterers are available, the physical features can be extracted using classical polarimetric processing techniques. The objective of this study is to evaluate the performance of the proposed full-rank polarimetric reconstruction by means of conventional three-component decomposition of T, and focusing on the consistency of vertical resolution and polarimetric scattering pattern of the scatterers. The outcomes from simulated and two different real data sets confirm that significant improvement can be achieved in the reconstruction quality with respect to conventional approaches.

scholarly journals Robust Korean License Plate Recognition Based on Deep Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4140
Author(s):  
Hanxiang Wang ◽  
Yanfen Li ◽  
L.-Minh Dang ◽  
Hyeonjoon Moon
Keyword(s):  
Synthetic Data ◽  
Super Resolution ◽  
Real Data ◽  
Vital Role ◽  
License Plate ◽  
License Plate Recognition ◽  
Single Character ◽  
New Type ◽  
The Government ◽  
Processing Techniques

With the rapid rise of private vehicles around the world, License Plate Recognition (LPR) plays a vital role in supporting the government to manage vehicles effectively. However, an introduction of new types of license plate (LP) or slight changes in the LP format can break previous LPR systems, as they fail to recognize the LP. Moreover, the LPR system is extremely sensitive to the conditions of the surrounding environment. Thus, this paper introduces a novel deep learning-based Korean LPR system that can effectively deal with existing challenges. The main contributions of this study include (1) a robust LPR system with the integration of three pre-processing techniques (defogging, low-light enhancement, and super-resolution) that can effectively recognize the LP under various conditions, (2) the establishment of two original Korean LPR approaches for different scenarios, including whole license plate recognition (W-LPR) and single-character license plate recognition (SC-LPR), and (3) the introduction of two Korean LPR datasets (synthetic data and real data) involving a new type of LP introduced by the Korean government. Through several experiments, the proposed LPR framework achieved the highest recognition accuracy of 98.94%.

scholarly journals Data Classification in Complex Networks via Pattern Conformation, Data Importance and Structural Optimization

2017 ◽  
Author(s):  
Murillo G. Carneiro ◽  
Liang Zhao
Keyword(s):  
Structural Optimization ◽  
Complex Networks ◽  
Data Classification ◽  
Real Data ◽  
Disease Diagnosis ◽  
Data Sets ◽  
Semantic Role Labeling ◽  
Wide Range ◽  
Heart Disease Diagnosis ◽  
Physical Features

Most data classification techniques rely only on the physical features of the data (e.g., similarity, distance or distribution), which makes them difficult to detect intrinsic and semantic relations among data items, such as the pattern formation, for instance. In this thesis, it is proposed classification methods based on complex networks in order to consider not only physical features but also capture structural and dynamical properties of the data through the network representation. The proposed methods comprise concepts of pattern conformation, data importance and network structural optimization, which are related to complex networks theory, learning systems, and bioinspired optimization. Extensive experiments demonstrate the good performance of our methods when compared against representative state-of-the-art methods over a wide range of artificial and real data sets, including applications in domains such as heart disease diagnosis and semantic role labeling.

scholarly journals Linear discriminant analysis with a generalization of the Moore–Penrose pseudoinverse

2013 ◽  
Vol 23 (2) ◽  
pp. 463-471 ◽  
Author(s):  
Tomasz Górecki ◽  
Maciej Łuczak
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Covariance Matrix ◽  
Full Rank ◽  
Real Data ◽  
Data Sets ◽  
New Approach ◽  
Linear Discriminant ◽  
Penrose Pseudoinverse

The Linear Discriminant Analysis (LDA) technique is an important and well-developed area of classification, and to date many linear (and also nonlinear) discrimination methods have been put forward. A complication in applying LDA to real data occurs when the number of features exceeds that of observations. In this case, the covariance estimates do not have full rank, and thus cannot be inverted. There are a number of ways to deal with this problem. In this paper, we propose improving LDA in this area, and we present a new approach which uses a generalization of the Moore-Penrose pseudoinverse to remove this weakness. Our new approach, in addition to managing the problem of inverting the covariance matrix, significantly improves the quality of classification, also on data sets where we can invert the covariance matrix. Experimental results on various data sets demonstrate that our improvements to LDA are efficient and our approach outperforms LDA.

scholarly journals Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1956
Author(s):  
Jingyu Cong ◽  
Xianpeng Wang ◽  
Xiang Lan ◽  
Mengxing Huang ◽  
Liangtian Wan
Keyword(s):  
Neural Network ◽  
Continuous Wave ◽  
Super Resolution ◽  
Mimo Radar ◽  
Target Localization ◽  
Estimation Accuracy ◽  
Low Resolution ◽  
Range Estimation ◽  
Resolution Image ◽  
Resolution Imaging

The traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. In this paper, a fast joint direction-of-arrival (DOA) and range estimation framework for target localization is proposed; it utilizes a very deep super-resolution (VDSR) neural network (NN) framework to accelerate the imaging process while ensuring estimation accuracy. Firstly, we propose a fast low-resolution imaging algorithm based on the Nystrom method. The approximate signal subspace matrix is obtained from partial data, and low-resolution imaging is performed on a low-density grid. Then, the bicubic interpolation algorithm is used to expand the low-resolution image to the desired dimensions. Next, the deep SR network is used to obtain the high-resolution image, and the final joint DOA and range estimation is achieved based on the reconstructed image. Simulations and experiments were carried out to validate the computational efficiency and effectiveness of the proposed framework.

Sign in / Sign up

Export Citation Format

Share Document