Qiang Yao

Sichuan University, Missouri University of Science and Technology

Papers

Total Citations

H-Index

About

Qiang Yao’s research bridges the gap between intelligent sensing and autonomous robotics, with a focus on computer vision, neural networks, and real-time decision-making systems. His most cited work, “Vision based nighttime pavement cracks pixel level detection by integrating infrared visible fusion and deep learning” (2024, 27 citations), introduces a novel fusion approach that combines infrared and visible imagery with deep learning to achieve precise, pixel-level crack detection under low-light conditions—a critical advancement for infrastructure monitoring and safety. Earlier, Yao pioneered the use of RAM-based neural networks for collision avoidance in mobile robots (2004, 12 citations), demonstrating that efficient, lightweight neural architectures can enable autonomous navigation on simple microprocessor systems, bypassing the need for high-end computing. This work highlighted his ability to solve practical robotics challenges with minimal hardware. Yao’s contributions are particularly notable for their applied impact: his nighttime detection system addresses a real-world need in civil engineering, while his earlier robotics work laid groundwork for cost-effective autonomous systems. With a career spanning foundational robotics to cutting-edge deep learning applications, Yao exemplifies how targeted neural network design can drive innovation across domains.