| Research
A fast surface-defect detection method based on Dense-Yolo network
To improve the performance of surface defect detection methods based on deep learning in practical applications, we propose a fast surface defect detection network called the Dense-Yolo network, which combines the strengths of DenseNet and YOLOv3.
Research on multi-layer space evacuation control strategy based on meta cellular automata
In this project, we built a two-story evacuation assistance system to observe the pedestrian information in order to solve the evacuation problem. Based on the observed information, the evacuation assistance system proposes a simple switch-based density control algorithm to adjust the guidance signal of the guidance assistance system dynamically.
Quadcopter design (UAV)
