A5035031106- Advanced Neural Network Applications
- Infrared Target Detection Methodologies
- Privacy-Preserving Technologies in Data
- Industrial Vision Systems and Defect Detection
- Internet Traffic Analysis and Secure E-voting
- Remote Sensing and LiDAR Applications
- Cryptography and Data Security
- Advanced SAR Imaging Techniques
- Advanced Image and Video Retrieval Techniques
China Three Gorges University
2022-2024
With the increase in wind power generation, turbine blades require regular inspections to ensure they continue operate safely. You only look once (YOLO) is one of most widely used object detection algorithms and easy deploy into drone devices. To enhance real-time small target defects blades, this paper proposes an improved attention feature balanced YOLO (AFB-YOLO) algorithm based on YOLOv5s. Specifically, AFB-YOLO improves pyramid network by using weighted fusion cross-scale connections....
Federated learning (FL) enables the training of a global model using clients' local datasets, leveraging their computing resources for efficient machine while preserving user privacy. This paper explores FL in wireless networks, focusing on client selection and bandwidth allocation as key factors impacting latency, covert constraint energy consumption. We propose per-round drift plus cost (PEDPC) algorithm to address this optimization problem from an online perspective. The performance PEDPC...
Accurate target detection technology on ships can improve the comprehensive perception ability of weapon equipment. For SAR ship in complex environments, false and missing alarms are serious. We design a new real-time algorithm 3S-YOLO images. Firstly, reconstruct network structure, adjust relationship between receptive field multiscale fusion, realize lightweight processing feature extraction fusion network. Then, is pruned compressed by FPGM pruning to accelerate reasoning speed. Finally,...
Target detection for aerial images has been the focus of research. However, there are several difficulties in image detection, such as complex backgrounds, high resolution, and a large number small targets UAV (Unmanned Aerial Vehicles) images. In order to achieve high-precision ground targets, lightweight target algorithm LATD-YOLO (Lightweight Image Detector) based on YOLOv7 is proposed this paper. Firstly, new network structure dedicated proposed, feature extraction fusion architectures...