Zhenming Lv
Papers
2
Total Citations
46
H-Index
2
About
Zhenming Lv is a leading researcher in intelligent infrastructure inspection, whose work bridges robotics and deep learning to solve critical challenges in civil engineering. His primary research areas include real-time defect detection, autonomous robotic inspection, and lightweight neural networks for infrastructure monitoring. Lv’s most influential contribution is the development of Enhanced RT-DETR, a real-time detection transformer for robotic inspection of underwater bridge pier cracks—a paper that has garnered 33 citations since 2024. This work addresses the hazardous and labor-intensive task of underwater structural assessment by enabling robots to autonomously identify cracks with high accuracy and speed. In parallel, his lightweight sewer pipe crack detection method, based on amphibious robots and an improved YOLOv8n architecture (13 citations), tackles the equally challenging problem of underground pipeline inspection. By optimizing neural networks for deployment on resource-constrained robotic platforms, Lv has made autonomous inspection both practical and scalable. His achievements demonstrate a rare ability to advance state-of-the-art computer vision while solving real-world infrastructure safety problems, making his work essential reading for researchers in robotic inspection, structural health monitoring, and applied deep learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2