A5028017247- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- UAV Applications and Optimization
- Vehicle License Plate Recognition
- Anomaly Detection Techniques and Applications
- Human Mobility and Location-Based Analysis
Donghua University
2024-2025
Hangzhou Dianzi University
2021
Modern city construction focuses on developing smart transportation, but the recognition of large number non-motorized vehicles in is still not sufficient. Compared to fixed equipment, drones have advantages image acquisition due their flexibility and maneuverability. With dataset collected from aerial images taken by drones, this study proposed a novel lightweight architecture for small objection detection based YOLO framework, named EBR-YOLO. Firstly, since targets application scenario are...
Modern city construction focuses on developing smart transportation, but the recognition of large number non-motorised vehicles in is still not sufficient. Compared to fixed equipment, drones have advantages image acquisition due their flexibility and maneuverability. On basis dataset collected from aerial images taken by drones, this study designs a vehicle system that combines with YOLOv8 algorithm Pyside6, providing data support recognize promoting further research recognition. In order...
The current crowd counting tasks rely on a fully convolutional network to generate density map that can achieve good performance. However, due the occlusion and perspective distortion in image, directly generated usually neglects scale information spatial contact information. To solve it, we proposed MDPDNet (Multiresolution Density maps Parallel Dilated convolutions’ Network) reduce influence of estimation. This is composed two modules: (1) parallel dilated convolution module (PDM) combines...