A5040776969- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Data Quality and Management
- Simulation and Modeling Applications
- Infrared Target Detection Methodologies
- Remote Sensing and LiDAR Applications
- Advanced Image Fusion Techniques
- Semantic Web and Ontologies
- Cybersecurity and Cyber Warfare Studies
- Advanced Computational Techniques and Applications
- Service-Oriented Architecture and Web Services
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
- 3D Surveying and Cultural Heritage
- Software System Performance and Reliability
- Information and Cyber Security
PLA Information Engineering University
2016-2025
The object detection of unmanned aerial vehicle (UAV) images has widespread applications in numerous fields; however, the complex background, diverse scales, and uneven distribution objects UAV make a challenging task. This study proposes convolution neural network transformer hybrid model to achieve efficient images, which three advantages that contribute improving performance. First, effective cross-shaped window (CSWin) can be used as backbone obtain image features at different levels,...
The SuperGlue algorithm, which integrates deep learning theory with the SuperPoint feature extraction operator and addresses matching problem using classical Sinkhorn method, has significantly enhanced efficiency become a prominent research focus. However, existing operators often struggle to extract high-quality features from extremely low-light or dark images, resulting in reduced accuracy. In this study, we propose novel method that combines multi-scale retinex color restoration (MSRCR)...
The development, deployment, and maintenance of the current space situational awareness (SSA) information system have become increasingly complex. However, researchers cannot flexibly conveniently apply research results to practical applications due lack basic platforms for SSA. Inspired by X as a Service (XaaS), we propose microservice-based platform SSA data analytics provide scaffold-like researchers. Based on microservice, architecture this is proposed meet requirements flexible...
To effectively guarantee the safety and efficiency of space activities, to meet needs different levels users for object situation (SOS) knowledge, formalized standardized SOS knowledge is needed assist cognition. A graph (KG), as a suitable technology that can formally express construct base, provide generation, representation intelligent service SOS. In this paper, an information based on KG (SOSKG) was constructed. Aimed at scales components in SOS, multi-granularity structure constructed,...
A digital twin city maps a virtual three-dimensional (3D) model to the geographic information system, constructs world, and integrates real sensor data achieve purpose of virtual–real fusion. Focusing on accuracy problem vision registration in scene, this study proposes 2D-3D method under inverse depth structural semantic constraints. First, perspective images scene were obtained by using view inverse-depth nascent technology, then features extracted two-line minimal solution set method....
Building instance extraction and recognition (BEAR) extracts further recognizes building instances in unmanned aerial vehicle (UAV) images, holds with paramount importance urban understanding applications. To address this challenge, we propose a unified network, BEAR-Former. Given the difficulty of due to small area multiple UAV developed novel multi-view learning method, Cross-Mixer. This method constructs cross-regional branch an intra-regional to, respectively, extract global context...
Reinforcing weak cyberspace assets is an urgent requirement to defend national cybersecurity. Cyberspace key terrain (CKT) a theory recently proposed for sensing posture. Identifying CKT in the asset layer essential supporting defense decisions. Existing methods ignore influence of multi-attribute correlation nodes and cyber attack mission (CAM) diversity, which restricts recognition accuracy CKT. To improve identification explore relationship between CAM, we propose improved cosine...
Visual place recognition (VPR) is a task that aims to predict the location of an image based on existing images. Because data can often be massive, extracting features efficiently critical. To solve problems model redundancy and poor time efficiency in feature extraction, this study proposes fast dual-feature extraction method tightly coupled lightweight network. The network extracts local global unified which has backbone. Learned step size quantization then performed reduce computational...
With the rapid development of aerospace and remote sensing technology, various high-resolution Earth Observation Systems (EOS) are widely used in economic, social, military other fields playing an increasingly prominent role construction Digital national strategic planning. The normal operation system is premise high quality data acquisition. Compared with ground observation mode, EOS itself surrounding environment more complex, its control mainly depends on all kinds Space Situational...