Yingna Su

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Yingna Su is a researcher in autonomous driving and computer vision, with key contributions in road detection, curb detection, and sensor calibration. Her work addresses critical challenges in perception systems for self-driving vehicles, particularly in handling occlusions, shadows, and small target detection. Her most cited paper, "Curb Detection for Road and Sidewalk Detection" (2018, 58 citations), proposes a novel curb detection paradigm that significantly improves obstacle avoidance and road understanding in complex urban environments. She also developed an illumination-invariant nonparametric model for urban road detection (14 citations), introducing a shadow removal method that enhances robustness under varying lighting conditions. In sensor fusion, Su proposed a two-step Lidar-camera calibration approach (2021, 6 citations) that combines coarse and fine alignment for accurate ego-motion estimation. Her work on camera motion estimation (2 citations) introduces a general elimination strategy for relative and absolute pose estimation, advancing geometric understanding in robotics. With a focus on practical, real-world applications, Su's research has direct implications for autonomous navigation, and her citation record reflects growing recognition in the field. Her interdisciplinary approach—integrating monocular cameras, LIDAR, and geometric models—positions her as a rising contributor to safe and reliable autonomous systems.