Defeng Liu

Jiangnan University, Wuxi Taihu Hospital

Papers

Total Citations

H-Index

About

Defeng Liu is a researcher whose work lies at the intersection of computer vision and mobile robotics, with a focus on visual tracking and camera parameter estimation. His most cited paper, “SECPNet—secondary encoding network for estimating camera parameters” (2021, 4 citations), introduces a novel deep learning architecture that improves the accuracy of camera pose estimation, a critical component for augmented reality and autonomous navigation. In his 2023 work, “Visual Object Tracking Method for Mobile Robots Based on DSST” (2 citations), Liu addresses the challenge of fast and precise object tracking in dynamic environments. He proposes an innovative fusion of the discriminative space scale tracking (DSST) correlation filter with a Kalman filter, enhanced by a confidence criterion based on oscillation severity and average peak-to-correlation energy (APCE). This approach significantly boosts tracking robustness and real-time performance for mobile robots. Though early in his career, Liu’s contributions demonstrate a clear trajectory toward practical, efficient solutions for real-world robotic vision systems, establishing him as an emerging voice in applied computer vision.