Yunchu Mei
Papers
2
Total Citations
5
H-Index
2
About
Yunchu Mei’s research lies at the intersection of deep learning and intelligent robotics for power infrastructure, with a focus on enabling autonomous maintenance in distribution networks. Her most cited work introduces an insulator instance segmentation method using Mask R-CNN, a deep learning framework that precisely identifies and segments insulators in power supply lines—a critical step toward automating grid inspection and reducing the burden of large-scale maintenance. This paper has garnered 3 citations, reflecting its relevance to the growing field of AI-driven power system monitoring. In parallel, her research on robot dynamic visual SLAM addresses the challenge of real-time localization and mapping in live working scenes of distribution networks, where wires are subject to movement from natural conditions. By integrating visual SLAM with robotic systems, she contributes to the development of smarter, more adaptive robots capable of operating safely in dynamic, high-stakes environments. Mei’s work is notable for its practical application to real-world grid challenges, bridging computer vision and robotics to enhance the efficiency and safety of power system maintenance.
Research Focus
Key Achievements
Top Papers
- 1Insulator instance segmentation based on deep learning network Mask RCNN3 citations · 2022
- 2