A5100397286- Advanced SAR Imaging Techniques
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Graph Labeling and Dimension Problems
- Radar Systems and Signal Processing
- Optical Systems and Laser Technology
- graph theory and CDMA systems
- Target Tracking and Data Fusion in Sensor Networks
- Microwave Imaging and Scattering Analysis
- Remote Sensing and Land Use
- Advanced Graph Theory Research
- Cryospheric studies and observations
- Robotics and Sensor-Based Localization
- Advanced Measurement and Detection Methods
- Remote-Sensing Image Classification
- Video Surveillance and Tracking Methods
- Underwater Acoustics Research
- Image Processing Techniques and Applications
- Soil Moisture and Remote Sensing
- Advanced Image and Video Retrieval Techniques
- Geophysical Methods and Applications
- Infrared Target Detection Methodologies
- Face and Expression Recognition
- Advanced Vision and Imaging
- Optical measurement and interference techniques
- Advanced Image Fusion Techniques
Sun Yat-sen University
2025
Southwest Hospital
2025
Army Medical University
2025
Beihang University
2015-2024
Southwest Petroleum University
2024
Lanzhou Jiaotong University
2011-2024
Chengdu Sport University
2024
Tongji University
2021-2024
University of California, San Diego
2024
Guilin University of Technology
2008-2023
Advertising posters are a commonly used form of information presentation to promote product. Producing advertising often takes much time and effort designers when confronted with abundant choices design elements layouts. This paper presents Vinci, an intelligent system that supports the automatic generation posters. Given user-specified product image taglines, Vinci uses deep generative model match set layouts for generating aesthetic poster. The also integrates online editing-feedback users...
Suppression technology of barrage jamming is an important approach to ensure the normal operation synthetic aperture radar (SAR) system. The detection and classification a necessary procedure in this technology. Unsuitable thresholds set traditional methods may reduce accuracy. In order avoid it, paper proposes new method for SAR based on convolutional neural network (CNN). signal model constructed statistical characteristics echo signal. Based this, data containing signals interference...
Spinocerebellar ataxia type 3 (SCA3), a neurodegenerative disorder caused by excess CAG repeats in the ATXN3 gene, leads to progressive cerebellar and other symptoms. The results of previous studies suggest that trace element dysregulation contributes onset. Here, we investigated relationships with repeat length, clinical severity, brain structural functional connectivity 45 patients SCA3 44 healthy controls (HCs). Blood levels lithium (Li), selenium (Se), copper (Cu) were significantly...
Spatial intelligence is a critical component of embodied AI, promoting robots to understand and interact with their environments. While recent advances have enhanced the ability VLMs perceive object locations positional relationships, they still lack capability precisely orientations-a key requirement for tasks involving fine-grained manipulations. Addressing this limitation not only requires geometric reasoning but also an expressive intuitive way represent orientation. In context, we...
Abstract Background Perineural invasion (PNI) is a hallmark feature of pancreatic ductal adenocarcinoma (PDAC), which occurs at high incidence and significantly contributes to PDAC lethality poor survival. Despite its prevalence association with prognosis, the molecular mechanisms underlying PNI in remain unclear. Methods We investigated clinical samples from two cohorts by UPLC/MS-MS profiled altered chemical RNA modifications tissues lesions. Dorsal root ganglion coculture systems sciatic...
The polar format algorithm (PFA) is a wavenumber domain imaging method for spotlight synthetic aperture radar (SAR). classic fixed-parameter PFA employs interpolation technique data correction. However, such an operation will induce heavy computational load and cause degradation in computation precision. To optimize image formation processing performance, this study presents novel parameter-adjusting PFA, which can implement SAR at extremely highly squint angle with obviously improved...
Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models difficult to effectively extract key features and share high computational complexity. To solve problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer is proposed for better handling SAR recognition tasks. In this work, firstly we propose Atrous-Inception module, which combines both atrous convolution inception module obtain rich...
To understand, predict, and control complex networked systems, a prerequisite is to reconstruct the network structure from observable data. Despite recent progress in reconstruction, binary-state dynamics that are ubiquitous nature, technology, society still present an outstanding challenge this field. Here we offer framework for reconstructing networks with by developing universal data-based linearization approach applicable systems linear, nonlinear, discontinuous, or stochastic governed...
Data videos are a genre of narrative visualization that communicates stories by combining data and motion graphics. While increasingly gaining popularity, few systematic reviews or structured analyses exist for their design. In this work, we introduce design space animated visual narratives in videos. The combines dimension animation techniques frequently used to facilitate communication with one strategies served such support story presentation. We derived our from the analysis 82...
As an important application in civilian surveillance, pedestrian counting is challenging due to the occlusion and cluttered background. In this paper, we present efficient people system based on regression template matching. This method can effectively overcome shortcomings of detecting tracking-based feature regression-based method. At same time, also introduce a practical public dataset named CASIA Pedestrian Counting Dataset. It contains richly annotated video images captured from daily...
Image formation from squinted sliding spotlight synthetic aperture radar (SAR) is limited by azimuth spectral folding and severe two dimension coupling.This paper presents an Extended Wavenumber Domain Algorithm (WDA) for highly SAR data processing.This algorithm adopts deramping approach to overcome the phenomenon.The chirp rate principle of choosing pulse repetition frequency (PRF) presented accommodate characteristic Doppler history.Subsequently, full focusing implemented WDA.Instead...
Radio frequency interference (RFI) is known to jam synthetic aperture radar (SAR) measurements, severely degrading the SAR imaging quality. The suppression of RFI in echo signals usually an underdetermined blind source separation problem. In this paper, we propose a novel method for multiclass detection and based on single shot multibox detector (SSD). First, echo-interference dataset established by randomly combining target signal with various types simulation, time–frequency form obtained...
Fractal networks are ubiquitous in nature, ranging from river to vascular networks. The ultimate goal of exploring these fractal networked systems lies controlling the dynamical processes that take place on them. We offer analytical results exactly understand our ability control dynamics regular terms identifying minimum number driver nodes required achieve full control. According exact controllability theory, an undirected network is completely determined by eigenvalue spectrum coupling...
The utilization of unmanned aerial vehicles (UAVs) is progressively expanding, thereby introducing novel risks to public safety and even the battlefield environment. Consequently, it becomes imperative detect non-cooperative UAVs. employment UAV sound signals for identifying nearby UAVs has garnered significant attention due its comprehensive coverage, independence from obstructions such as trees, cost-effectiveness. However, practical implementation hindered by rapid attenuation sound,...
Abstract Our understanding of how vision functions as primates actively navigate the real-world is remarkably sparse. As most data have been limited to chaired and typically head-restrained animals, synergistic interactions different motor actions/plans inherent active sensing – e.g. eyes, head, posture, movement, etc. - on visual perception are largely unknown. To address this considerable gap in knowledge, we developed an innovative wireless head-mounted eye tracking system called CEREBRO...
A novel approach to detecting and tracking a moving target using synthetic aperture radar (SAR) images is proposed in this paper. Achieved with the particle filter (PF) based track-before-detect (TBD) algorithm, capable of low signal-to-noise ratio (SNR) SAR systems, which traditional track-after-detect (TAD) inadequate for. By incorporating signal model into ambiguity azimuth position radial velocity resolved while tracking, leads directly true estimation. With sub-area substituted for...
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), most algorithms of which have employed and relied on sufficient training samples to receive a strong discriminative classification model, has remained challenging task in recent years, among the challenge SAR data acquisition further insight into intuitive features images are main concerns. In this paper, deep transferred multi-level feature fusion attention network with dual optimized loss, called (MFFA-SARNET), is proposed...
In recent years, impressive performance of deep learning technology has been recognized in synthetic aperture radar (SAR) automatic target recognition (ATR). Since a large amount annotated data are required this technique, it poses trenchant challenge to the issue obtaining high rate through less labeled data. To overcome problem, inspired by contrastive learning, we proposed novel framework named batch instance discrimination and feature clustering (BIDFC). framework, different from that...
Among high-squint high-resolution (HSHR) synthetic aperture radar imaging algorithms, nonlinear chirp scaling algorithm (NLCSA) and its extensions, such as extended NLCSA (ENLCSA), have a common drawback in that they all neglect the spatial variations of linear range migration (LRM) Doppler centroid, thus, only targets specific central slant plane can be strictly focused. In this letter, we show by using new NLCSA, focused ground under HSHR conditions. Based on more accurate 2-D spectrum,...
In this paper, approaches to facial expression recognition based on two dimension methods are studied. 2D feature extraction include 2DPCA, 2DLDA and Generalized Low Rank Approximation of Matrices (GLRAM) which usually used in face or data compression. After features extracted, support vector machine classifier is for classification. Extensive experiments carried out Japanese Female Facial Expression database (JAFFE) study the influence ratio results also compared with that tradition 1D such...
The spaceborne stripmap range sweep synthetic aperture radar (SS-RSSAR) is a new concept SAR system that images the region of interest (ROI) with ROI-orientated strips, which, unlike traditional SAR, are allowed to be not parallel satellite orbit. SS-RSSAR imaging challenging problem because echoes wide have strong spatial varieties, especially in high-squint geometries, and hard focused by single swath. algorithms could solve this cost-ineffectively dividing an ROI into many subswaths for...