Detecção de Fissuras Utilizando Redes Neurais Convolucionais
Resumo
Fissuras em concreto representam manifestações patológicas e ocorrem por diversos motivos, mesmo que haja boas práticas na fase de construção. Em estruturas de grande porte, como pontes, túneis e barragens é exigido que, com certa periodicidade, ocorra inspeções visuais com objetivo de detectar, diagnosticar a causa e quando possível, reparar a fissura. Nos casos que não é possível reparar a fissura, se deve acompanhar o seu comportamento. Muitas técnicas computacionais para a detecção de fissuras têm sido propostas mas suas aplicações são limitadas pois as imagens de fissuras tendem a variar muito e neste caso, extrair informações como a localização da fissura em uma imagem requer que seja realizada uma segmentação a nível de pixel. Neste contexto, esse trabalho apresenta uma proposta utilizando o Detectron2, inspirado na rede neural convolucional Mask R-CNN, que oferece suporte para detecção de objetos, segmentação de instâncias, segmentação de panorâmica, e segmentação de semântica.
Referências
L. Ali, F. Alnajjar, H. A. Jassmi, M. Gocho, W. Khan, and M. A. Serhani, Performance evaluation of deep cnn-based crack detection and localization techniques for concrete structures, Sensors, vol. 21, no. 5, 2021. [Online]. Available: https://www.mdpi.com/1424-8220/21/5/1688
M. N. Abou-Zeid, F. Fouad, R. Leistikow, R. Poston, J. Barlow, D. Fowler, P. A. Lipphardt, R. J. Rhoads, F. Barth, G. T. Halvorsen, E. Nawy, J. W. Roberts, J. Best, W. Hansen, K. Nemati, A. Scanlon, D. Darwin, H. Haynes, K. A. Pashina, A. Schokker, J. F. Duntemann, R. Frosch, and J. West, Causes, evaluation, and repair of cracks in concrete structures, 2007.
Z. Liu, Y. Cao, Y. Wang, and W. Wang, Computer vision-based concrete crack detection using u-net fully convolutional networks, Automation in Construction, vol. 104, pp. 129139, 2019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0926580519301244
C . F. O zgenel and A. G. Sorguc, Performance comparison of pretrained convolutional neural networks on crack detection in buildings, in ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, vol. 35. IAARC Publications, 2018, pp. 18.
R. Khandelwal, Computer vision: Instance segmentation with mask r-cnn, Disponivel em: [link]. Acesso em: 06 marco 2020, 2019.
S. S. Damaceno and R. O. Vasconcelos, Inteligencia artificial: uma breve abordagem sobre seu conceito real e o conhecimento popular, Caderno de Graduac ao-Ciencias Exatas e Tecnologicas-UNIT-SERGIPE, vol. 5, no. 1, p. 11, 2018.
Y. Wu, A. Kirillov, F. Massa, W.-Y. Lo, and R. Girshick, Detectron2, https://github.com/facebookresearch/detectron2, 2019.
J. S. Lapa, Patologia, recuperac ao e reparo das estruturas de concreto, Monografia, Especializac ao em Construc ao CivilUniversidade Federal de Minas Gerais, Belo Horizonte, 2008.
F. F. F. Peres, Estrutura conceitual para integrac ao da auscultac ao de fissuras em barragens de concreto com realidade aumentada, 2017.
J. D. P. Massucatto, Aplicac ao de conceitos de redes neurais convolucionais na classificac ao de imagens de folhas, B.S. thesis, Universidade Tecnologica Federal do Parana, 2018.
D. S. Academy, Deep learning book, 2019.
R. B. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CoRR, vol. abs/1311.2524, 2013. [Online]. Available: http://arxiv.org/abs/1311.2524
R. B. Girshick, Fast R-CNN, CoRR, vol. abs/1504.08083, 2015. [Online]. Available: http://arxiv.org/abs/1504.08083
S. Ren, K. He, R. B. Girshick, and J. Sun, Faster R-CNN: towards real-time object detection with region proposal networks, CoRR, vol. abs/1506.01497, 2015. [Online]. Available: http://arxiv.org/abs/1506.01497
K. He, G. Gkioxari, P. Dollar, and R. B. Girshick, Mask R-CNN, CoRR, vol. abs/1703.06870, 2017. [Online]. Available: http://arxiv.org/abs/1703.06870
P. Sharma, Computer vision tutorial: Implementing mask r-cnn for image segmentation, Disponivel em: [link]. Acesso em: 19 julho 2021, 2019.
L. Zhang, F. Yang, Y. D. Zhang, and Y. J. Zhu, Road crack detection using deep convolutional neural network, in Image Processing (ICIP), 2016 IEEE International Conference on. IEEE, 2016, pp. 37083712.
Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, Automatic road crack detection using random structured forests, IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 12, pp. 34343445, 2016.
R. Amhaz, S. Chambon, J. Idier, and V. Baltazart, Automatic crack detection on two-dimensional pavement images: An algorithm based on minimal path selection.
M. Eisenbach, R. Stricker, D. Seichter, K. Amende, K. Debes, M. Sesselmann, D. Ebersbach, U. Stoeckert, and H.-M. Gross, How to get pavement distress detection ready for deep learning? a systematic approach. in International Joint Conference on Neural Networks (IJCNN), 2017, pp. 20392047.
F. Yang, L. Zhang, S. Yu, D. Prokhorov, X. Mei, and H. Ling, Feature pyramid and hierarchical boosting network for pavement crack detection, arXiv preprint arXiv:1901.06340, 2019.
L. Cui, Z. Qi, Z. Chen, F. Meng, and Y. Shi, Pavement distress detection using random decision forests, in International Conference on Data Science. Springer, 2015, pp. 95102.
L. Yang, B. Li, W. Li, Z. Liu, G. Yang, and J. Xiao, Deep concrete inspection using unmanned aerial vehicle towards cssc database, in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017, pp. 2428.
Y. Liu, J. Yao, X. Lu, R. Xie, and L. Li, Deepcrack: A deep hierarchical feature learning architecture for crack segmentation, Neurocomputing, vol. 338, pp. 139153, 2019.
Q. Zou, Y. Cao, Q. Li, Q. Mao, and S. Wang, Cracktree: Automatic crack detection from pavement images, Pattern Recognition Letters, vol. 33, no. 3, pp. 227238, 2012.
COCO, Detection evaluation and metric, 2020. [Online]. Available: https://cocodataset.org/#detection-eval
M. N. Abou-Zeid, F. Fouad, R. Leistikow, R. Poston, J. Barlow, D. Fowler, P. A. Lipphardt, R. J. Rhoads, F. Barth, G. T. Halvorsen, E. Nawy, J. W. Roberts, J. Best, W. Hansen, K. Nemati, A. Scanlon, D. Darwin, H. Haynes, K. A. Pashina, A. Schokker, J. F. Duntemann, R. Frosch, and J. West, Causes, evaluation, and repair of cracks in concrete structures, 2007.
Z. Liu, Y. Cao, Y. Wang, and W. Wang, Computer vision-based concrete crack detection using u-net fully convolutional networks, Automation in Construction, vol. 104, pp. 129139, 2019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0926580519301244
C . F. O zgenel and A. G. Sorguc, Performance comparison of pretrained convolutional neural networks on crack detection in buildings, in ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, vol. 35. IAARC Publications, 2018, pp. 18.
R. Khandelwal, Computer vision: Instance segmentation with mask r-cnn, Disponivel em: [link]. Acesso em: 06 marco 2020, 2019.
S. S. Damaceno and R. O. Vasconcelos, Inteligencia artificial: uma breve abordagem sobre seu conceito real e o conhecimento popular, Caderno de Graduac ao-Ciencias Exatas e Tecnologicas-UNIT-SERGIPE, vol. 5, no. 1, p. 11, 2018.
Y. Wu, A. Kirillov, F. Massa, W.-Y. Lo, and R. Girshick, Detectron2, https://github.com/facebookresearch/detectron2, 2019.
J. S. Lapa, Patologia, recuperac ao e reparo das estruturas de concreto, Monografia, Especializac ao em Construc ao CivilUniversidade Federal de Minas Gerais, Belo Horizonte, 2008.
F. F. F. Peres, Estrutura conceitual para integrac ao da auscultac ao de fissuras em barragens de concreto com realidade aumentada, 2017.
J. D. P. Massucatto, Aplicac ao de conceitos de redes neurais convolucionais na classificac ao de imagens de folhas, B.S. thesis, Universidade Tecnologica Federal do Parana, 2018.
D. S. Academy, Deep learning book, 2019.
R. B. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CoRR, vol. abs/1311.2524, 2013. [Online]. Available: http://arxiv.org/abs/1311.2524
R. B. Girshick, Fast R-CNN, CoRR, vol. abs/1504.08083, 2015. [Online]. Available: http://arxiv.org/abs/1504.08083
S. Ren, K. He, R. B. Girshick, and J. Sun, Faster R-CNN: towards real-time object detection with region proposal networks, CoRR, vol. abs/1506.01497, 2015. [Online]. Available: http://arxiv.org/abs/1506.01497
K. He, G. Gkioxari, P. Dollar, and R. B. Girshick, Mask R-CNN, CoRR, vol. abs/1703.06870, 2017. [Online]. Available: http://arxiv.org/abs/1703.06870
P. Sharma, Computer vision tutorial: Implementing mask r-cnn for image segmentation, Disponivel em: [link]. Acesso em: 19 julho 2021, 2019.
L. Zhang, F. Yang, Y. D. Zhang, and Y. J. Zhu, Road crack detection using deep convolutional neural network, in Image Processing (ICIP), 2016 IEEE International Conference on. IEEE, 2016, pp. 37083712.
Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, Automatic road crack detection using random structured forests, IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 12, pp. 34343445, 2016.
R. Amhaz, S. Chambon, J. Idier, and V. Baltazart, Automatic crack detection on two-dimensional pavement images: An algorithm based on minimal path selection.
M. Eisenbach, R. Stricker, D. Seichter, K. Amende, K. Debes, M. Sesselmann, D. Ebersbach, U. Stoeckert, and H.-M. Gross, How to get pavement distress detection ready for deep learning? a systematic approach. in International Joint Conference on Neural Networks (IJCNN), 2017, pp. 20392047.
F. Yang, L. Zhang, S. Yu, D. Prokhorov, X. Mei, and H. Ling, Feature pyramid and hierarchical boosting network for pavement crack detection, arXiv preprint arXiv:1901.06340, 2019.
L. Cui, Z. Qi, Z. Chen, F. Meng, and Y. Shi, Pavement distress detection using random decision forests, in International Conference on Data Science. Springer, 2015, pp. 95102.
L. Yang, B. Li, W. Li, Z. Liu, G. Yang, and J. Xiao, Deep concrete inspection using unmanned aerial vehicle towards cssc database, in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017, pp. 2428.
Y. Liu, J. Yao, X. Lu, R. Xie, and L. Li, Deepcrack: A deep hierarchical feature learning architecture for crack segmentation, Neurocomputing, vol. 338, pp. 139153, 2019.
Q. Zou, Y. Cao, Q. Li, Q. Mao, and S. Wang, Cracktree: Automatic crack detection from pavement images, Pattern Recognition Letters, vol. 33, no. 3, pp. 227238, 2012.
COCO, Detection evaluation and metric, 2020. [Online]. Available: https://cocodataset.org/#detection-eval
Publicado
18/10/2021
Como Citar
OLIVEIRA, Raianny Proença C. de; MAURICIO, Claudio Roberto M.; SANTOS, Valéria Nunes dos; PERES, Fabiana Frata F..
Detecção de Fissuras Utilizando Redes Neurais Convolucionais. In: WORKSHOP DE TRABALHOS DA GRADUAÇÃO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 34. , 2021, Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 212-217.
DOI: https://doi.org/10.5753/sibgrapi.est.2021.20041.
