Shao-Kai Zhu

Papers

Total Citations

H-Index

About

Shao-Kai Zhu is a researcher advancing the frontiers of visual Simultaneous Localization and Mapping (SLAM), with a core focus on improving robotic perception in challenging environments. His most-cited work, "Monocular Visual SLAM based on VGG Feature Point Extraction" (2020), tackles a critical limitation in the field: the significant drop in localization accuracy that occurs in low-texture and illumination-changing settings. By integrating deep learning-based VGG feature extraction into traditional SLAM frameworks, Zhu demonstrated a robust method for maintaining reliable mapping and localization where conventional algorithms fail. This contribution, which has garnered 5 citations, addresses a persistent bottleneck in autonomous navigation for mobile robots and augmented reality systems. Zhu’s research sits at the intersection of computer vision, deep learning, and robotics, offering practical solutions for real-world deployment. His work is particularly notable for bridging the gap between theoretical feature extraction techniques and applied SLAM performance, making it a valuable reference for students and researchers seeking to enhance visual odometry under non-ideal conditions.