AI Super Resolution for Structural Damage Detection From Low Quality Sources
Presentation Type
Poster
Student
Yes
Track
Methodology
Abstract
The identification of damages following natural disasters is of critical importance, as it plays a crucial role in mitigating the risk of subsequent harm, including additional structural damage, injuries, or fatalities. Artificial intelligence (AI) presents significant advantages in this domain by offering faster, more precise, and scalable assessments compared to traditional reliance on expert evaluations alone. When integrated with expert analysis, AI has the potential to enhance the efficiency and accuracy of damage detection, facilitating a comprehensive and rapid assessment of affected structures. Such capabilities are vital for minimizing future risks and enabling timely and effective recovery efforts. This study proposes an AI-based super-resolution method designed to detect structural damages from low-quality data sources. By enhancing the clarity and detail of damage assessments, the proposed approach provides critical information to first responders, enabling them to take informed and calculated measures in disaster response scenarios. This methodology aims to bridge existing gaps in damage detection systems, contributing to improved resilience and preparedness in the face of natural disasters.
Start Date
2-7-2025 1:00 PM
End Date
2-7-2025 2:30 PM
AI Super Resolution for Structural Damage Detection From Low Quality Sources
Volstorff A
The identification of damages following natural disasters is of critical importance, as it plays a crucial role in mitigating the risk of subsequent harm, including additional structural damage, injuries, or fatalities. Artificial intelligence (AI) presents significant advantages in this domain by offering faster, more precise, and scalable assessments compared to traditional reliance on expert evaluations alone. When integrated with expert analysis, AI has the potential to enhance the efficiency and accuracy of damage detection, facilitating a comprehensive and rapid assessment of affected structures. Such capabilities are vital for minimizing future risks and enabling timely and effective recovery efforts. This study proposes an AI-based super-resolution method designed to detect structural damages from low-quality data sources. By enhancing the clarity and detail of damage assessments, the proposed approach provides critical information to first responders, enabling them to take informed and calculated measures in disaster response scenarios. This methodology aims to bridge existing gaps in damage detection systems, contributing to improved resilience and preparedness in the face of natural disasters.