Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images

J. M. Vazquez-Nicolas, Erik Zamora, I. Gonzalez-Hernandez, Rogelio Lozano, Humberto Sossa

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

© 2018 IEEE. Building inspection searching for superficial defects, such as cracks, is a vital task because such damages cause economic losses or put at risk the integrity of people. For this reason, different ways to reduce the costs and risks through the use of robotic systems that allow make inspections have been studied. Among these robotic systems, we have the unmanned aerial vehicles (UAV) that allow reaching difficult access places permitting better inspection. In this work, we propose using convolutional neuronal networks for crack recognition from images captured by an UAV. To carry out the training task of the network, a database of cracks in walls was built from images collected from the Internet. The training of the network prompted encouraging results with a 95% accuracy over the training set. Experimental results of crack recognition in images were carried out validating the application of the proposal.
Original languageAmerican English
Pages654-659
Number of pages588
DOIs
StatePublished - 31 Aug 2018
Event2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018 -
Duration: 31 Aug 2018 → …

Conference

Conference2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018
Period31/08/18 → …

Fingerprint

Unmanned aerial vehicles (UAV)
Inspection
Cracks
Robotics
Internet
Defects
Economics
Costs

Cite this

Vazquez-Nicolas, J. M., Zamora, E., Gonzalez-Hernandez, I., Lozano, R., & Sossa, H. (2018). Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images. 654-659. Paper presented at 2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018, . https://doi.org/10.1109/ICUAS.2018.8453390
Vazquez-Nicolas, J. M. ; Zamora, Erik ; Gonzalez-Hernandez, I. ; Lozano, Rogelio ; Sossa, Humberto. / Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images. Paper presented at 2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018, .588 p.
@conference{014cbf9d811247158d60e791131be57e,
title = "Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images",
abstract = "{\circledC} 2018 IEEE. Building inspection searching for superficial defects, such as cracks, is a vital task because such damages cause economic losses or put at risk the integrity of people. For this reason, different ways to reduce the costs and risks through the use of robotic systems that allow make inspections have been studied. Among these robotic systems, we have the unmanned aerial vehicles (UAV) that allow reaching difficult access places permitting better inspection. In this work, we propose using convolutional neuronal networks for crack recognition from images captured by an UAV. To carry out the training task of the network, a database of cracks in walls was built from images collected from the Internet. The training of the network prompted encouraging results with a 95{\%} accuracy over the training set. Experimental results of crack recognition in images were carried out validating the application of the proposal.",
author = "Vazquez-Nicolas, {J. M.} and Erik Zamora and I. Gonzalez-Hernandez and Rogelio Lozano and Humberto Sossa",
year = "2018",
month = "8",
day = "31",
doi = "10.1109/ICUAS.2018.8453390",
language = "American English",
pages = "654--659",
note = "2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018 ; Conference date: 31-08-2018",

}

Vazquez-Nicolas, JM, Zamora, E, Gonzalez-Hernandez, I, Lozano, R & Sossa, H 2018, 'Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images', Paper presented at 2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018, 31/08/18 pp. 654-659. https://doi.org/10.1109/ICUAS.2018.8453390

Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images. / Vazquez-Nicolas, J. M.; Zamora, Erik; Gonzalez-Hernandez, I.; Lozano, Rogelio; Sossa, Humberto.

2018. 654-659 Paper presented at 2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images

AU - Vazquez-Nicolas, J. M.

AU - Zamora, Erik

AU - Gonzalez-Hernandez, I.

AU - Lozano, Rogelio

AU - Sossa, Humberto

PY - 2018/8/31

Y1 - 2018/8/31

N2 - © 2018 IEEE. Building inspection searching for superficial defects, such as cracks, is a vital task because such damages cause economic losses or put at risk the integrity of people. For this reason, different ways to reduce the costs and risks through the use of robotic systems that allow make inspections have been studied. Among these robotic systems, we have the unmanned aerial vehicles (UAV) that allow reaching difficult access places permitting better inspection. In this work, we propose using convolutional neuronal networks for crack recognition from images captured by an UAV. To carry out the training task of the network, a database of cracks in walls was built from images collected from the Internet. The training of the network prompted encouraging results with a 95% accuracy over the training set. Experimental results of crack recognition in images were carried out validating the application of the proposal.

AB - © 2018 IEEE. Building inspection searching for superficial defects, such as cracks, is a vital task because such damages cause economic losses or put at risk the integrity of people. For this reason, different ways to reduce the costs and risks through the use of robotic systems that allow make inspections have been studied. Among these robotic systems, we have the unmanned aerial vehicles (UAV) that allow reaching difficult access places permitting better inspection. In this work, we propose using convolutional neuronal networks for crack recognition from images captured by an UAV. To carry out the training task of the network, a database of cracks in walls was built from images collected from the Internet. The training of the network prompted encouraging results with a 95% accuracy over the training set. Experimental results of crack recognition in images were carried out validating the application of the proposal.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85053880060&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85053880060&origin=inward

U2 - 10.1109/ICUAS.2018.8453390

DO - 10.1109/ICUAS.2018.8453390

M3 - Paper

SP - 654

EP - 659

ER -

Vazquez-Nicolas JM, Zamora E, Gonzalez-Hernandez I, Lozano R, Sossa H. Towards automatic inspection: Crack recognition based on Quadrotor UAV-taken images. 2018. Paper presented at 2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018, . https://doi.org/10.1109/ICUAS.2018.8453390