Mingze Yuan
Papers
3
Total Citations
27
H-Index
3
About
Mingze Yuan is a researcher whose work sits at the intersection of robotics, computer vision, and industrial automation. His primary research areas include sensor calibration, robotic perception, and intelligent fault detection for industrial systems. Yuan made a significant contribution to robotic perception with his unifying framework for monocular visual-inertial and robotic-arm calibration, which addresses critical inaccuracies in traditional methods—a foundational step for reliable robot pose estimation and environmental sensing. This work has garnered 13 citations. In the domain of industrial maintenance, he pioneered the use of Hidden Markov Models for fault detection in industrial robot RV reducers using acoustic emission measurements, offering a more reliable alternative to conventional techniques; this paper has been cited 11 times. More recently, Yuan has explored 360° optical flow computation using tangent images, expanding the capabilities of omnidirectional vision for robotics and computer vision. His research demonstrates a consistent focus on solving practical, high-impact problems in robotic perception and industrial reliability, making his work valuable for both academic researchers and engineers in the field.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3360° Optical Flow using Tangent Images3 citations · 2021