Xavier Maldague is a Professor in the Department of Electrical and Computer Engineering at Université Laval's Faculty of Science and Engineering, with over 35 years of research in infrared thermography and non-destructive testing methodologies. His work spans theoretical algorithm development to practical industrial applications across aerospace, cultural heritage, medical diagnostics, and infrastructure inspection domains. Dr. Maldague's research interests focus on advanced thermal imaging techniques, sensor fusion systems, and machine learning applications for defect detection and material characterization. His work has evolved from fundamental thermographic algorithms in the 1990s to current research integrating deep learning, drone-based platforms, and multi-sensor fusion systems for industrial inspection. Key areas include pulsed thermography, line-scan techniques, coplanar capacitive sensing, and hyperspectral infrared imaging. Analysis of his 15 most recent publications reveals a strong emphasis on deep learning integration with traditional thermographic methods, particularly for defect detection in composite materials, cultural heritage objects, and infrastructure components. His recent work shows increasing focus on multi-modal data fusion, drone-enabled inspection platforms, and synthetic data generation for training machine learning models. The research spans both theoretical algorithm development and practical implementation across diverse application domains. Dr. Maldague has maintained a highly productive research trajectory with consistent publication output, particularly in high-impact journals such as Sensors, IEEE Access, and Remote Sensing. His work demonstrates strong international collaboration, with numerous co-authors from European institutions alongside his primary Canadian research team. His research group appears to focus on developing practical inspection systems that bridge theoretical image processing with real-world industrial applications, with recent emphasis on automation, deep learning integration, and multi-sensor approaches to enhance detection capabilities and reliability in non-destructive testing scenarios.
