A5027200194- Infrastructure Maintenance and Monitoring
- Advanced Neural Network Applications
- Industrial Vision Systems and Defect Detection
- Adhesion, Friction, and Surface Interactions
- Iterative Learning Control Systems
- Railway Engineering and Dynamics
- Vehicle License Plate Recognition
- Remote Sensing and LiDAR Applications
Hohai University
2024
Inner Mongolia Electric Power Survey & Design Institute (China)
2024
Road defect detection is critical step for road maintenance periodic inspection. Current methodologies exhibit drawbacks such as low accuracy, slow speed, and the inability to support edge deployment real-time detection. To solve this issue, we introduce an improved YOLOv8 model. Firstly, designed EMA Faster Block structure using partial convolution replace Bottleneck in C2f module, enhanced module was labeled C2f-Faster-EMA. Secondly, model speed by introducing SimSPPF instead of SPPF....
The railway track, as a fundamental infrastructure for rail transport, directly impacts the safety of train operations. Track defects such cracks and bolt loosening, if not detected repaired in time, can lead to severe accidents. In recent years, deep learning-based track defect detection algorithms have achieved good results. However, there are still some issues that need further research, low accuracy complex scenarios limited capability diverse components. To address these problems, this...
Abstract Foreign Object Debris (FOD) poses a significant safety risk to aircraft operations, making efficient and accurate detection methods crucial. Existing techniques often struggle meet the demands of busy airports due limitations in real-time performance accuracy. To address these challenges, we proposed lightweight FOD model based on YOLOv10. By incorporating PConv EMA attention mechanisms, our enhances accuracy, achieving 0.4% increase mAP@50 0.7% improvement mAP@50-95 compared...