Yingchu Wang

Papers

Total Citations

H-Index

About

Dr. Yingchu Wang is a pioneering researcher at the intersection of computer vision, edge computing, and structural health monitoring (SHM). Their work centers on developing efficient, real-time deep learning systems for infrastructure inspection, with a particular focus on crack segmentation—a critical technique for early defect detection and long-term safety assurance. Wang’s most notable contribution, the CrackESS system, introduces a self-prompting framework that enables high-accuracy crack segmentation directly on edge devices, overcoming the computational limitations of traditional cloud-dependent approaches. This innovation bridges the gap between advanced AI and practical, on-site deployment, making SHM more accessible and responsive. With over 2 citations on their seminal 2025 paper, Wang’s research is gaining traction among engineers and computer scientists seeking scalable solutions for aging infrastructure. By integrating prompt engineering with lightweight neural architectures, they have set a new standard for autonomous defect detection in resource-constrained environments. Wang’s work not only advances the field of SHM but also demonstrates how cutting-edge AI can be tailored for real-world, low-power applications—a critical step toward smarter, safer cities.