Qinhan Yang

Papers

Total Citations

H-Index

About

Qinhan Yang is a researcher in robotics and computer vision, with a primary focus on visual-inertial odometry (VIO) and deep learning for autonomous navigation. His most notable contribution is the development of LPL-VIO, a monocular visual-inertial odometry system that integrates deep learning-based point and line features to enhance localization accuracy in challenging environments. This work addresses critical limitations of traditional VIO systems, particularly in low-texture or repetitive scenes where point features alone fail. Yang’s research bridges the gap between classical geometric methods and modern deep learning, offering robust solutions for real-time SLAM applications. While his citation count is still growing, his work has already garnered attention in the field, with LPL-VIO serving as a foundation for further advancements in sensor fusion and autonomous systems. Yang’s contributions are particularly relevant for students and researchers exploring the intersection of deep learning and state estimation, as his approach demonstrates how neural networks can improve feature extraction and matching in VIO pipelines. His ongoing work promises to shape the next generation of robust, learning-based localization systems for drones, robots, and autonomous vehicles.