Luzhen Ma
Papers
1
Total Citations
3
H-Index
1
About
Luzhen Ma is a researcher advancing the frontier of visual simultaneous localization and mapping (SLAM) by integrating semantic and geometric cues. Her primary research areas include monocular SLAM, semantic mapping, and planar feature extraction. In her most notable work, "TXSLAM: A Monocular Semantic SLAM Tightly Coupled with Planar Text Features" (2022), Ma proposes a novel system that treats text features as textured planes rich in semantic information. By tightly coupling these planar text features into the SLAM pipeline, her method achieves more accurate camera pose estimation than conventional approaches. This work addresses a critical challenge in robotics and augmented reality: leveraging real-world text (e.g., signs, labels) as robust, repeatable landmarks. Although early in its citation trajectory (3 citations), TXSLAM represents a creative fusion of computer vision and natural language cues, opening new directions for semantically aware navigation. Ma’s contributions highlight the potential of exploiting everyday visual information—like street signs—to enhance autonomous system reliability, making her a promising voice in the evolution of intelligent perception.
Research Focus
Key Achievements
Top Papers
- 1