A5031223263- Blind Source Separation Techniques
- Advanced Neural Network Applications
- Wireless Communication Networks Research
- Industrial Vision Systems and Defect Detection
- Infrastructure Maintenance and Monitoring
- Video Surveillance and Tracking Methods
- Advanced Wireless Communication Techniques
- Gait Recognition and Analysis
- Algorithms and Data Compression
- Human Mobility and Location-Based Analysis
- 3D Surveying and Cultural Heritage
- Wireless Signal Modulation Classification
- Indoor and Outdoor Localization Technologies
- Energy Efficient Wireless Sensor Networks
- Advanced Computational Techniques and Applications
- 3D Shape Modeling and Analysis
- Advanced Vision and Imaging
- Image Retrieval and Classification Techniques
- Underwater Vehicles and Communication Systems
- Remote-Sensing Image Classification
- Advanced Adaptive Filtering Techniques
- Image Enhancement Techniques
- Wireless Communication Security Techniques
- Security in Wireless Sensor Networks
- Non-Destructive Testing Techniques
Zhejiang University of Science and Technology
2022-2025
Hangzhou Dianzi University
2019
Applying computer vision techniques to rail surface defect detection (RSDD) is crucial for preventing catastrophic accidents. However, challenges such as complex backgrounds and irregular shapes persist. Previous methods have focused on extracting salient object information from a pixel perspective, thereby neglecting valuable high- low-frequency image information, which can better capture global structural information. In this study, we design pixel-aware frequency conversion network...
Crowd counting has received significant attention in recent years due to its practical applications. In order address the specific characteristics of RGB and thermal images, we have developed graph enhancement transformer aggregation network (GETANet) for generating representative density maps. Our approach incorporates several innovative modules enhance accuracy. Firstly, introduced a position-adaptive module that effectively counts individuals' positions integrates features extracted from...
Although networks with traditional convolutional neural network (CNN) backbones have achieved remarkable results in red-green-blue–depth (RGB-D) semantic segmentation, convolution cannot easily capture remote dependencies. Transformers encounter no such difficulties and can obtain richer global information. Therefore, we design an auxiliary context-information enhancement (ACENet) using Swin Transformer as branch to assist the CNN backbone network. First, input outputs of each stage...
The conventional frequency hopping (FH) system is susceptible to malicious jamming due the prearranged table. In this paper, we develop a bivariate agility (BFA) communication improve anti-jamming capability by assigning time-varying characteristics parameters such as fixed interval and rate in FH. Our goal find optimal strategy environment maximize signal-to-noise ratio (SINR). We formulate parameter decision problem Markov process (MDP). Then, propose deep deterministic policy gradient...