Sha Yang
Papers
1
Total Citations
3
H-Index
1
About
Sha Yang has made significant contributions to the field of intelligent power inspection, with a primary focus on computer vision and deep learning for robotic systems. Her most notable work centers on advancing object detection algorithms, specifically through the development of enhanced YOLOv3 models tailored for power infrastructure monitoring. Yang’s key innovation addresses a critical challenge in the industry: the frequent misdetection of small or diverse targets during automated inspections. She proposed two optimized network architectures—YOLOv3-g, designed for GPU-based systems, and YOLOv3-mini, adapted for CPU environments—which improve detection accuracy and efficiency without sacrificing real-time performance. Her research, published in 2020, has garnered 3 citations and is foundational for engineers seeking robust, hardware-adaptive solutions for power line and equipment inspection. By bridging the gap between algorithm performance and practical deployment constraints, Yang’s work directly supports the reliability and safety of automated power grids. Her contributions are particularly valuable for researchers and practitioners working at the intersection of robotics, energy infrastructure, and edge computing, offering scalable models that enhance operational precision in challenging real-world environments.
Research Focus
Key Achievements
Top Papers
- 1