National University of Defense Technology

About: National University of Defense Technology is a education organization based out in Changsha, China. It is known for research contribution in the topics: Computer science & Radar. The organization has 39430 authors who have published 40181 publications receiving 358979 citations. The organization is also known as: Guófáng Kēxuéjìshù Dàxué & NUDT.

Image-Domain Estimation of Wall Parameters for Autofocusing of Through-the-Wall SAR Imagery

Abstract: Estimation of the basic parameters, wall thickness and dielectric constant, is important in through-the-wall radar imaging. Ambiguities in wall characteristics will degrade the image focusing quality of synthetic-aperture radar. In order to obtain a quick and precise estimation of wall parameters, an equivalent propagation model of an electromagnetic wave in the air-wall-air medium is first developed in this paper. According to the developed propagation model, two filter-based approaches, denoted respectively as the echo-domain-filter-based method and the image-domain-filter-based method, are proposed to estimate wall thickness and dielectric constant by adjusting the two corresponding parameters of the echo-domain filter or the image-domain filter to obtain the best focusing quality of behind-the-wall targets. The processing schemes of the two methods show that the image-domain-filter-based method is more efficient because it does not involve imaging processing in each adjustment. Moreover, the image-domain-filter-based method is accelerated by reducing the dimension of searching space to better the computational efficiency further. Simulation results show that the proposed accelerating image-domain-filter-based method can provide quick and precise estimation of wall parameters.

A Study of the Human Flesh Search Engine: Crowd-Powered Expansion of Online Knowledge

Abstract: This first comprehensive empirical study of a search function that originated in China examines its tremendous growth in recent years and its uniquely rich online/offline interactions.

Neural network-aided adaptive unscented Kalman filter for nonlinear state estimation

Abstract: The extended Kalman filter (EKF) is well known as a state estimation method for a nonlinear system and has been used to train a multilayered neural network (MNN) by augmenting the state with unknown connecting weights. However, EKF has the inherent drawbacks such as instability due to linearization and costly calculation of Jacobian matrices, and its performance degrades greatly, especially when the nonlinearity is severe. In this letter, first a more robust learning algorithm for an MNN-based on unscented Kalman filter (UKF) is derived. Since it gives a more accurate estimate of the linkweights, the convergence performance is improved. The algorithm is then extended further to develop a NN-aided UKF for nonlinear state estimation. The NN in this algorithm is used to approximate the uncertainty of the system model due to mismodeling, extreme nonlinearities, etc. The UKF is used for both NN online training and state estimation simultaneously. Simulation results show that the new algorithm is very effective and is closer to optimal fashion in nonlinear filtering compared with traditional methods

Airborne Vision-Based Navigation Method for UAV Accuracy Landing Using Infrared Lamps

Abstract: In this paper, an airborne vision-based navigation method for Unmanned Aerial Vehicle (UAV) accuracy landing is presented. In this method, a visible light camera integrated with a Digital Signal Processing (DSP) processor is installed on the UAV and a 940 nm optical filter is fixed in front of the camera lens. In addition, four infrared light-emitting diode (LED) lamps whose emission wavelengths are 940 nm are placed behind ideal landing site on the runway. In this way, the infrared lamps in the image are distinct even if the image background is complicated. In the image processing procedure, firstly maximum between-class variance algorithm and region growing algorithm are used to determine candidate infrared lamp regions in the images. Then Negative Laplacian of Gaussian (NLOG) operator is applied to detect and track centers of the infrared lamps in the images. The space position and attitude of the camera can be obtained according to the corresponding relationship between image coordinates and space coordinates of the infrared lamp centers. Finally, high precision space position of the UAV can be calculated according to the installation relationship between the camera and the UAV. Plenty of real flight and static precision experiments have proved the validity and accuracy of the proposed method.

Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network

Abstract: In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed graph convolutional network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long-range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2-D image grids. Second, we refine the graph edge weight and the connective relationships among image regions simultaneously by learning the improved similarity measurement and the “edge filter,” so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in faithful region representations, and vice versa. The experiments carried out on four real-world benchmark data sets demonstrate the effectiveness of the proposed method.