Guest Editors
Assoc. Prof. Sheng Xiang
Email: xiangsheng@cqupt.edu.cn
Affiliation: College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China
Homepage:
Research Interests: prognostics and health management, large language model, efficient AI, multivariate time series
Assoc. Prof. Quan Qian
Email: qian_1998@uestc.edu.cn
Affiliation: School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China
Homepage:
Research Interests: transfer learning, process control, intelligent fault diagnosis and RUL prediction
Dr. Junyu Qi
Email: junyu.qi@kit.edu
Affiliation: Institute of Engineering Mechanics, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany
Homepage:
Research Interests: condition monitoring, anomaly detection, industrial AI
Summary
This Special Issue, entitled Deep Visual Recognition for Structural Durability and Health Monitoring, aims to provide a systematic forum for recent advances in vision-driven intelligent methods for structural assessment. With the increasing availability of visual sensing data and the rapid evolution of deep learning, visual recognition has become a key enabling technology for non-contact, large-scale, and high-resolution monitoring of engineering structures. However, its deployment in real-world structural health monitoring (SHM) still faces critical challenges, including complex environmental interference, limited labeled data, domain generalization, and computational constraints.
This Special Issue seeks contributions that address these challenges from both methodological and application perspectives. Topics of interest include, but are not limited to, deep visual recognition models (e.g., CNNs, Transformers, and foundation models) for damage detection and durability assessment; multimodal fusion of vision and time-series data for enhanced structural understanding; self-supervised and few-shot learning under data-scarce conditions; and efficient and edge-oriented AI frameworks for real-time SHM.
By integrating advances in computer vision, machine learning, and structural engineering, this Special Issue aims to foster the development of robust, generalizable, and deployable visual intelligence solutions, ultimately contributing to improved safety, reliability, and lifecycle management of critical infrastructure.
Keywords
deep visual recognition, structural health monitoring, structural durability, multimodal learning, edge AI
Login
Register
Submit a Paper
Propose a Special lssue