Mengxia Tang
Papers
1
Total Citations
3
H-Index
1
About
Mengxia Tang’s research centers on computer vision and autonomous navigation, with a particular focus on semantic segmentation for outdoor environments. In her most-cited work, “Encoder–Decoder Structure Fusing Depth Information for Outdoor Semantic Segmentation” (2023), Tang addresses a critical challenge in scene understanding: improving segmentation accuracy by integrating depth data from RGB-D images. Her proposed encoder-decoder architecture effectively fuses spatial and depth features, enabling robots to better interpret complex outdoor scenes—a key capability for safe autonomous navigation. While this paper has garnered 3 citations to date, its impact lies in advancing a foundational task for robotics and autonomous systems. Tang’s work contributes to the growing body of research that leverages multimodal sensor fusion to enhance machine perception, bridging the gap between raw sensor data and actionable scene understanding. Her approach offers a practical solution for deploying semantic segmentation in real-world autonomous navigation, where robustness to varying lighting and terrain is essential. As the field moves toward more reliable self-driving and robotic systems, Tang’s contributions provide a valuable step forward in making outdoor scene analysis both more accurate and more efficient.
Research Focus
Key Achievements
Top Papers
- 1