Min Yang

Beijing Technology and Business University

Papers

Total Citations

H-Index

About

Min Yang is a versatile researcher whose work spans computer vision, intelligent transportation systems, and human-computer interaction. He has made notable contributions to the automatic detection of pavement distresses, most prominently through his 2022 study optimizing the YOLOv5s deep learning architecture for identifying road surface damage. This work addresses a critical real-world challenge — enabling timely pavement repair to prevent structural deterioration and reduce traffic accidents — and has garnered 51 citations, reflecting its strong uptake within the infrastructure monitoring and computer vision communities. Yang's research demonstrates a practical engineering mindset, focusing on refining existing state-of-the-art models to improve accuracy and efficiency in complex, real-world visual environments where object occlusion and category imbalance pose significant challenges. Earlier in his career, Yang explored the frontier of telepresence and human-robot interaction, developing a novel touchscreen-based interface — the Touchable Live Video Image User Interface (TIUI) — that allowed remote operators to interact more intuitively with telepresence robots. Together, these contributions illustrate a researcher driven by applied innovation, consistently working to bridge emerging technologies with tangible societal benefits across transportation safety and remote collaboration.