A5050629769- Infrared Target Detection Methodologies
- Advanced Measurement and Detection Methods
- Advanced Image Fusion Techniques
- Video Surveillance and Tracking Methods
- Simulation and Modeling Applications
- Misinformation and Its Impacts
- Infrared Thermography in Medicine
- Functional Brain Connectivity Studies
- Image Retrieval and Classification Techniques
- Advanced Neuroimaging Techniques and Applications
- Image Enhancement Techniques
- Advanced Vision and Imaging
- Computer Graphics and Visualization Techniques
- Currency Recognition and Detection
- Remote Sensing and Land Use
- Robotics and Sensor-Based Localization
- Advanced MRI Techniques and Applications
- 3D Modeling in Geospatial Applications
- Image and Object Detection Techniques
- Geological Modeling and Analysis
- Remote-Sensing Image Classification
- Opinion Dynamics and Social Influence
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Satellite Image Processing and Photogrammetry
Northwestern Polytechnical University
2018-2024
Xi'an Jiaotong University
2023-2024
Aerial infrared target tracking is the basis of many weapon systems, especially air‐to‐air missile. Till now, it still challenging research to track aircraft in event complex background. In this paper, we focus on developing an algorithm that could fast and accurately based image sequence. We proposed a framework composed tracker T correlation filter detector D deep learning, which call combined detecting (CTAD). With such collaboration, enjoys both high efficiency provided by strong...
As an excellent single-stage object detector based on neural networks, YOLOv5 has found extensive applications in the industrial domain; however, it still exhibits certain design limitations. To address these issues, this paper proposes Efficient Scale Fusion YOLO (ESF-YOLO). Firstly, Multi-Sampling Conv Module (MSCM) is designed, which enhances backbone network’s learning capability for low-level features through multi-scale receptive fields and cross-scale feature fusion. Secondly, to...
In the field of automatic target recognition and tracking, long-term tracking for aerial infrared has been recently seen with great interest. Although deep trackers correlation filtering offer competitive results on performance, problems deformation, abrupt motion, heavy occlusion, out view still remain unsolved. addition, since this paper focus images, it is also important to consider that images have a significant drawbacks, such as low resolution, contrast, lack textures. paper, we adopt...
Abstract Functional connectivity (FC) is a widely used imaging parameter of functional magnetic resonance (fMRI). However, low reliability has been concern among researchers, particularly in small-sample-size studies. Previous studies have shown that FC based on longer fMRI scans was more reliable, therefore, feasible solution to predict long-scan FCs using existing short-scan FCs. This study explored three different generalized linear models (GLMs) the human connectome project (HCP)...
Infrared dim and small target detection has an important role in the infrared thermal imaging seeker, search tracking system, space-based system other applications. Inspired by human visual (HVS), based on fusion of significant features targets, present study proposes algorithm for complex backgrounds. Firstly, order to calculate saliency map, proposed initially uses difference Gaussian (DoG) contourlet filters preprocessing fusion, respectively. Then multi-scale improved local contrast...
Robustness and accuracy are the two main challenging tasks in feature-based UAV (Unmanned Aerial Vehicle) color remote sensing image registration. In this paper, an optimal threshold registration algorithm is proposed. Firstly, a modified descriptor constructed adding information to increase descriptor's distinctiveness robustness. Based on primeval calculated by SURF, got with space transformation superimposed descriptor. Secondly, method put forward rate. Finally, novel purification...
Image complexity metric is an important part of automatic target recognition(ATR) performance evaluation, the relationship between infrared image and recognition studied, which for imaging system prediction evaluation comparison algorithms. Aiming at this problem, method proposed. Firstly, mechanism analyzed to find main factors affecting recognition. The defined from similarity degree clutter submergence clutter, clarify influence To increase universality complexity, concept feature space...
Summarized the mainly algorithms of terrain three-dimensional visualization in virtual reality, for large-scale data organization war zone simulation, analyzed characteristic change scene, according to motion regulation and idea layer block, presented organize principle external static blocks index regulation, large system pressure process scene update, synthesize available visibility culling methods, with data, could operate a high frame rate.
In the field of automatic target recognition and tracking, traditional image complexity metrics, such as statistical variance signal-to-noise ratio, all focus on single-frame images.However, there are few researches about sequence.To solve this problem, a criterion evaluating sequence is proposed.Firstly, to characterize quantitatively, two metrics for measuring sequence, namely feature space similarity degree global background (FSSDGB) occultation local (FSODLB) developed.Here, FSSDGB...
Small infrared moving target detection has an important role in the sea-based search and tracking, maritime area surveillance other applications. This method aims to detect small targets with sea-sky background. The present study proposes a algorithm for based on spatio-temporal saliency fusion. contourlet analysis edge extraction are carried out concurrent design. In order effectively suppress background improve signal-clutter ratio, spectral residual is combined above mentioned methods...