Xiaohong Qian

Zhejiang University of Science and Technology

Papers

Total Citations

H-Index

About

Xiaohong Qian is a researcher specializing in computer vision and autonomous driving, with a particular focus on semantic segmentation for robot navigation. Their most notable contribution is the development of THCANet (Two-layer Hop Cascaded Asymptotic Network), a novel deep learning architecture designed for road-scene understanding using RGB-D images. This work, published in 2023 and garnering 32 citations, introduces an innovative two-layer cascaded approach that efficiently processes both color and depth information to achieve robust semantic segmentation in complex driving environments. The method's asymptotic design allows for progressive refinement of segmentation results, making it particularly valuable for real-time robotic perception systems. Qian's research addresses critical challenges in autonomous navigation, including accurate scene parsing under varying lighting conditions and complex urban scenarios. By integrating depth information with traditional RGB data, their work enhances the reliability of vision-based systems for self-driving vehicles and mobile robots. The THCANet architecture represents a meaningful step forward in bridging the gap between computational efficiency and segmentation accuracy, contributing to the broader field of intelligent transportation systems and autonomous robotics.