Bei Pan
Papers
1
Total Citations
9
H-Index
1
About
Bei Pan is a researcher whose work lies at the intersection of deep learning and marine robotics, with a primary focus on efficient object detection in challenging underwater environments. Her most notable contribution is the development of an attention mechanism-enhanced Ghost-YOLOv5 model for underwater fish detection, a paper that has garnered 9 citations. This work addresses a critical real-world problem: the computational constraints of underwater robots, which cannot support the large-scale deep convolutional neural networks typically used for high-accuracy object detection. By innovatively integrating attention mechanisms to improve feature extraction while maintaining a lightweight architecture, Pan has advanced the practical deployment of AI in marine biology and aquaculture. Her research demonstrates a keen ability to balance algorithmic performance with real-world hardware limitations, making her work valuable for both computer vision and robotics communities. Pan’s contributions are particularly relevant for researchers exploring edge computing applications in environmental monitoring, where efficiency and accuracy must coexist.
Research Focus
Key Achievements
Top Papers
- 1