Junyu Han
Papers
2
Total Citations
20
H-Index
1
About
Junyu Han is a rising researcher in autonomous systems and computer vision, whose work focuses on advancing visual perception for robotics and self-driving vehicles. Han’s primary contributions lie in Visual Simultaneous Localization and Mapping (VSLAM) and Visual Place Recognition (VPR), where they tackle the critical challenges of robustness, precision, and computational efficiency. Their most cited paper, "BASL-AD SLAM: A Robust Deep-Learning Feature-Based Visual SLAM System With Adaptive Motion Model" (2024, 19 citations), introduces a novel deep-learning framework that enhances localization accuracy in dynamic environments—a key requirement for advanced driver assistance and autonomous driving. In parallel, Han’s work on "BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition" (2024, 1 citation) explores the use of binary neural networks to dramatically reduce computational overhead while maintaining high recognition performance, enabling deployment on resource-constrained platforms. By bridging deep learning with practical, real-time navigation, Han is shaping the next generation of efficient, reliable visual systems. Their research holds significant promise for making autonomous navigation both smarter and more accessible, marking them as a notable contributor to the field.
Research Focus
Key Achievements
Top Papers
- 1
- 2