Xiaoting Liao
Papers
1
Total Citations
53
H-Index
1
About
Xiaoting Liao is a leading researcher in the application of deep learning to infrastructure monitoring, with a primary focus on automated sewer defect detection and structural health assessment. Her most impactful work, "Real-time sewer defect detection based on YOLO network, transfer learning, and channel pruning algorithm" (2023), has garnered 53 citations and represents a significant advance in deploying lightweight, efficient computer vision models for real-time inspection of underground pipelines. Liao’s major contribution lies in integrating transfer learning with channel pruning techniques, enabling high-accuracy defect identification (such as cracks, blockages, and joint displacements) while dramatically reducing computational overhead—a critical step toward practical, on-site deployment in resource-constrained environments. Her research bridges the gap between state-of-the-art object detection algorithms and civil engineering needs, offering scalable solutions for aging urban infrastructure. By demonstrating that sophisticated YOLO-based networks can be optimized for real-time performance without sacrificing precision, Liao has opened new avenues for automated, non-destructive evaluation. Her work is widely cited by researchers in both computer vision and civil engineering, underscoring its interdisciplinary impact and its potential to transform maintenance practices in water and wastewater systems worldwide.
Research Focus
Key Achievements
Top Papers
- 1