A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Concrete Crack Detection from Video Footage for Structural Health Monitoring
https://orcid.org/http://orcid.org/0000-0001-6028-1228
https://orcid.org/http://orcid.org/0000-0003-2884-3969
https://orcid.org/http://orcid.org/0000-0003-4230-7580
https://orcid.org/http://orcid.org/0000-0002-8480-0595
Non-destructive imaging is largely encouraged as a preliminary investigation for damage identification on concrete structural surfaces. Cracks are basic signatures for any structure to initiate the damage. As the whole world is currently connected with lot of cameras all around for various purposes either it be for traffic studies, accident analysis, thefts, natural or human disasters. Alternatively, the same video frames obtained from cameras located in or on the structure can be analysed even for the structural health monitoring. This study aims at identifying the cracks from images mined out of the video frames apart from the crack propagation and length of the crack. Convolution Neural Network is used to train over the images from the video captured during the laboratory compressive strength experiment on a concrete cube to examine and estimate the crack properties. This methodology can be extended to the real-life scenario to alert the damages caused in the structures.
Concrete Crack Detection from Video Footage for Structural Health Monitoring
https://orcid.org/http://orcid.org/0000-0001-6028-1228
https://orcid.org/http://orcid.org/0000-0003-2884-3969
https://orcid.org/http://orcid.org/0000-0003-4230-7580
https://orcid.org/http://orcid.org/0000-0002-8480-0595
Non-destructive imaging is largely encouraged as a preliminary investigation for damage identification on concrete structural surfaces. Cracks are basic signatures for any structure to initiate the damage. As the whole world is currently connected with lot of cameras all around for various purposes either it be for traffic studies, accident analysis, thefts, natural or human disasters. Alternatively, the same video frames obtained from cameras located in or on the structure can be analysed even for the structural health monitoring. This study aims at identifying the cracks from images mined out of the video frames apart from the crack propagation and length of the crack. Convolution Neural Network is used to train over the images from the video captured during the laboratory compressive strength experiment on a concrete cube to examine and estimate the crack properties. This methodology can be extended to the real-life scenario to alert the damages caused in the structures.
Concrete Crack Detection from Video Footage for Structural Health Monitoring
https://orcid.org/http://orcid.org/0000-0001-6028-1228
https://orcid.org/http://orcid.org/0000-0003-2884-3969
https://orcid.org/http://orcid.org/0000-0003-4230-7580
https://orcid.org/http://orcid.org/0000-0002-8480-0595
Non-destructive imaging is largely encouraged as a preliminary investigation for damage identification on concrete structural surfaces. Cracks are basic signatures for any structure to initiate the damage. As the whole world is currently connected with lot of cameras all around for various purposes either it be for traffic studies, accident analysis, thefts, natural or human disasters. Alternatively, the same video frames obtained from cameras located in or on the structure can be analysed even for the structural health monitoring. This study aims at identifying the cracks from images mined out of the video frames apart from the crack propagation and length of the crack. Convolution Neural Network is used to train over the images from the video captured during the laboratory compressive strength experiment on a concrete cube to examine and estimate the crack properties. This methodology can be extended to the real-life scenario to alert the damages caused in the structures.
Concrete Crack Detection from Video Footage for Structural Health Monitoring
Lecture Notes in Civil Engineering
Rizzo, Piervincenzo (editor) / Milazzo, Alberto (editor) / Kadarla, Sushmita (author) / Beeram, Sree Keerthe (author) / Kalapatapu, Prafulla (author) / Pasupuleti, Venkata Dilip Kumar (author)
European Workshop on Structural Health Monitoring ; 2020
2021-01-11
10 pages
Article/Chapter (Book)
Electronic Resource
English
Structural Damage Identification from Video Footage Using Artificial Intelligence
| Springer Verlag | 2022
Automatic Detection of Construction Work using Surveillance Video Footage
| British Library Conference Proceedings | 2008
| European Patent Office | 2019
| British Library Online Contents | 2006