A5004552450- Advanced Neural Network Applications
- Fire Detection and Safety Systems
- Anomaly Detection Techniques and Applications
- Power Line Inspection Robots
- Industrial Vision Systems and Defect Detection
- IoT-based Smart Home Systems
- Human Pose and Action Recognition
- Context-Aware Activity Recognition Systems
- Fault Detection and Control Systems
- Video Surveillance and Tracking Methods
Beijing University of Posts and Telecommunications
2022
Guilin University of Electronic Technology
2022
South China University of Technology
2022
To protect lives and equipment, a robust, reliable, expandable fire monitoring system is critical to detect react in campus situation. Thus, this paper proposes YOLOv5-based directly deployable on existing terminals, computers, other IoT terminals. The proposed effectively fires various scenarios all day long. Our deep learning model has been trained using images scene videos. experimental evaluations different end devices demonstrate that our achieves an appealing performance monitoring.
This paper proposes a method of checking wiring electric cabinets based on improved YOLOv5 and PP-OCRv3 to resolve the problems low efficiency, high manpower consumption, lengthy time-consuming manual in quality inspection stage modern industrial cabinet production. research indicates novel neural network structure called YOLOv5s-CBS that is YOLOv5s structure. The coordinated attention mechanism added C3 module backbone structure, BiFPN introduced neck loss function changed from CIoU SIoU,...