Boying Li

Papers

Total Citations

H-Index

About

Boying Li is a robotics and computer vision researcher whose work centers on simultaneous localization and mapping (SLAM), with a particular focus on integrating semantic understanding into visual navigation systems. Li is best known for pioneering the TextSLAM framework, a novel approach that treats detected text objects in man-made environments as rich planar features within the SLAM pipeline. By leveraging both the geometric structure and semantic meaning of text — a ubiquitous element in urban and indoor scenes — Li's method significantly enhances the robustness and accuracy of visual localization compared to conventional feature-based approaches. Introduced in preliminary form in 2019 and substantially developed through publications in 2020 and 2023, the TextSLAM system has garnered over 80 cumulative citations, reflecting its growing influence in the robotics and autonomous navigation communities. The 2023 iteration notably advanced the framework by enabling on-the-fly semantic extraction and updating, improving data association in challenging real-world conditions. Li's contributions represent an important bridge between classical geometric SLAM and the emerging field of semantic mapping, offering practical solutions for autonomous robots and vehicles operating in human-centric environments.