Summary
The proposal is about the Forensic Analysis of Concrete through Image Processing (FACIP), which offers several improvements over traditional methods of forensic analysis (FA) of concrete. Unlike manual inspection, the proposed method automates and streamlines the process, reducing human effort and evaluation time. FA of concrete is commonly used to determine particle size, shape, aggregate ratio, porosity, and other physical characteristics that affect concrete performance. This project aims to develop an innovative approach that utilizes image processing (IP) and Convolutional Neural Networks (CNN) to enhance FA of concrete structures. By accurately and efficiently detecting, characterizing, and quantifying various concrete defects such as cracks, spalling, corrosion, and delamination, the project aims to extract intricate patterns and features from concrete images through deep learning, improving FA accuracy. This ambitious objective pushes the boundaries of current research in FA of concrete, opening the door to discoveries and advancements. By combining IP and CNN for FACIP, the research aims to develop innovative methodologies and tools that surpass the limitations of existing techniques, such as Core Cutting, Schmidt Hammer, and UPVs, providing accurate and reliable analysis results. This contributes to developing more effective concrete maintenance, repair, and structural integrity assessment strategies. Ultimately, the project aims to provide concrete forensic experts with advanced, reliable, and time-efficient analysis methods, enhancing concrete forensic investigations' overall accuracy and effectiveness.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101153307 |
| Start date: | 01-06-2024 |
| End date: | 31-05-2026 |
| Total budget - Public funding: | - 226 751,00 Euro |
Cordis data
Original description
The proposal is about the Forensic Analysis of Concrete through Image Processing (FACIP), which offers several improvements over traditional methods of forensic analysis (FA) of concrete. Unlike manual inspection, the proposed method automates and streamlines the process, reducing human effort and evaluation time. FA of concrete is commonly used to determine particle size, shape, aggregate ratio, porosity, and other physical characteristics that affect concrete performance. This project aims to develop an innovative approach that utilizes image processing (IP) and Convolutional Neural Networks (CNN) to enhance FA of concrete structures. By accurately and efficiently detecting, characterizing, and quantifying various concrete defects such as cracks, spalling, corrosion, and delamination, the project aims to extract intricate patterns and features from concrete images through deep learning, improving FA accuracy. This ambitious objective pushes the boundaries of current research in FA of concrete, opening the door to discoveries and advancements. By combining IP and CNN for FACIP, the research aims to develop innovative methodologies and tools that surpass the limitations of existing techniques, such as Core Cutting, Schmidt Hammer, and UPVs, providing accurate and reliable analysis results. This contributes to developing more effective concrete maintenance, repair, and structural integrity assessment strategies. Ultimately, the project aims to provide concrete forensic experts with advanced, reliable, and time-efficient analysis methods, enhancing concrete forensic investigations' overall accuracy and effectiveness.Status
SIGNEDCall topic
HORIZON-MSCA-2023-PF-01-01Update Date
01-01-2025
Geographical location(s)
