Xidian University

About: Xidian University is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Antenna (radio) & Synthetic aperture radar. The organization has 32099 authors who have published 38961 publications receiving 431820 citations. The organization is also known as: University of Electronic Science and Technology at Xi'an & Xīān Diànzǐ Kējì Dàxué.

Image Sharpness Assessment by Sparse Representation

Abstract: Recent advances in sparse representation show that overcomplete dictionaries learned from natural images can capture high-level features for image analysis. Since atoms in the dictionaries are typically edge patterns and image blur is characterized by the spread of edges, an overcomplete dictionary can be used to measure the extent of blur. Motivated by this, this paper presents a no-reference sparse representation-based image sharpness index. An overcomplete dictionary is first learned using natural images. The blurred image is then represented using the dictionary in a block manner, and block energy is computed using the sparse coefficients. The sharpness score is defined as the variance-normalized energy over a set of selected high-variance blocks, which is achieved by normalizing the total block energy using the sum of block variances. The proposed method is not sensitive to training images, so a universal dictionary can be used to evaluate the sharpness of images. Experiments on six public image quality databases demonstrate the advantages of the proposed method.

Active Transfer Learning Network: A Unified Deep Joint Spectral–Spatial Feature Learning Model for Hyperspectral Image Classification

Abstract: Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning (TL) that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral–spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active TL is then exploited to transfer the pretrained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domains by the corresponding active learning (AL) strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel AL strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross data set and intraimage; and 3) the learned deep joint spectral–spatial feature representation is more generic and robust than many joint spectral–spatial feature representations. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular data sets.

Radar Cross Section Reduction of a Microstrip Antenna Based on Polarization Conversion Metamaterial

Abstract: A novel method aimed at reducing radar cross section (RCS) under incident waves with both $x$ - and $y$ -polarizations, with the radiation characteristics of the antenna preserved, is presented and investigated. The goal is accomplished by the implementation of the polarization conversion metamaterial (PCM) and the principle of passive cancellation. As a test case, a microstrip patch antenna is simulated and experimentally measured to demonstrate the proposed strategy for dramatic radar cross section reduction (RCSR). Results exhibit that in-band RCSR is as much as 16 dB compared to the reference antenna. In addition, the PCM has a contribution to a maximum RCSR value of 14 dB out of the operating band. With significant RCSR and unobvious effect on the radiation performance of the antenna, the proposed method has a wide application for the design of other antennas with a requirement of RCS control.

New Parameter Estimation and Detection Algorithm for High Speed Small Target

Abstract: Target detection and parameter estimation are the principal problems of radar applications. The detection and parameter estimation for high-speed small targets are challenging for narrowband radar since the target may only occupy one range cell with small reflectivity. In addition, the high speed makes the target shift through range cells during the observation period, which makes it difficult to improve the target's reflecting energy coherent accumulation and signal-to-noise ratio (SNR). An algorithm for high-speed small target detection and parameter estimation with narrowband radar is proposed in this paper. Firstly three target motion parameters, i.e., the cross-range frequency modulation rate, ambiguous Doppler frequency, and fold factor are estimated one by one. Then based on the estimated parameters, a target detection method is proposed. In addition, we also analyze the detection performance under estimation error. After that, an improved method for fold factor estimation is presented. Simulation results have proved the validity of the proposed algorithm.