Papers
6
Total Citations
78
H-Index
5
About
Suiwu Zheng is a pioneering researcher whose work sits at the intersection of manifold learning, dynamic visual tracking, and robotic vision systems. His most influential contribution, "Learning an Intrinsic-Variable Preserving Manifold for Dynamic Visual Tracking" (2009, 49 citations), addresses a fundamental challenge in computer science: how to extract low-dimensional intrinsic variables from high-dimensional visual data for robust object tracking. This work builds upon the landmark manifold learning framework published in *Science* in 2000, extending it into practical, real-time applications. Zheng further advanced the field by developing manifold-based methods for tracking multiple people in crowded scenes with occlusion reasoning, tackling one of the most difficult problems in robotic perception. His research portfolio also demonstrates remarkable breadth, including innovative work on underwater image matching for autonomous underwater robots (2017) and distributed event-triggered filtering for flexible robotic manipulators (2021), the latter incorporating semi-Markov models for enhanced control system performance. Zheng’s contributions have laid critical groundwork for making manifold learning a practical tool in dynamic, real-world environments, with his methods directly applicable to surveillance, human-robot interaction, and autonomous navigation systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Tracking feature extraction based on manifold learning framework9 citations · 2011
- 3
- 4Underwater image matching by incorporating structural constraints6 citations · 2017
- 5
- 6Tracking uncooperative person using a dynamic vision platform3 citations · 2010