Shan Du

Fudan University, University of British Columbia

Papers

Total Citations

H-Index

About

Shan Du is a researcher whose work bridges computer vision, robotics, and intelligent control systems. Her research primarily focuses on video tracking, monocular depth estimation, and adaptive fuzzy control, with applications spanning underwater biology, autonomous navigation, and human-computer interaction. Du’s most cited paper, “Obtaining three-dimensional trajectory of multiple fish in water tank via video tracking” (2018, 23 citations), introduced a novel method for reconstructing 3D movement paths from 2D video, enabling non-invasive behavioral studies in aquatic environments—a valuable tool for marine biology and environmental monitoring. In a more recent contribution, “A Lightweight Self-Supervised Training Framework for Monocular Depth Estimation” (2022, 4 citations), she addressed the growing demand for low-complexity depth sensing in robotics and augmented reality, proposing an efficient training paradigm that reduces reliance on labeled data. Du has also advanced control theory with “MIMO fuzzy adaptive control systems based on fuzzy semi-tensor product” (2023, 2 citations), developing a fuzzy controller for multivariable nonlinear systems with uncertainty. Her work demonstrates a versatile ability to tackle complex, real-world problems—from tracking fish in murky water to enabling machines to perceive depth—making her a rising voice in applied AI and intelligent systems.