A Deep Learning Approach to Vegetation Images Recognition in Buildings: a Hyperparameter Tuning Case Study
Keywords:Deep Learning, Convolutional Neural Networks, Vegetation images recognition, hyperparameter tuning
Deep Learning methods have important applications in digital image processing. However, the literature lacks further studies that propose machine learning models to images classification in civil construction area. For example, the vegetation recognition on facades can be relevant in identifying the degradation and abandonment of buildings. Thus, the objective of this paper is to propose an Convolutional Neural Networks (CNN) approach to vegetation images recognition in buildings. For this, a database with urban images (low altitude) captured by a drone in Zurich (Switzerland) was adopted. In addition, a rigorous hyperparameters tuning methodology for the CNN model is presented. After adjusting the hyperparameters and the final model, the system achieved 90% of accuracy in the test stage. It should also be noted that CNN correctly classified 97.8% of the positive class (with vegetation on the facade) in test images.
S. J. Russell and P. Norving, Artificial Intelligence. Campus, 3st ed., 2013.
I. N. Silva, D. H. Spatti, and R. A. Flauzino, Redes Neurais Artificiais Para Engenharia e Ciˆencias Aplicadas: fundamentos te´oricos e aspectos pr´aticos, 2nd ed., Ed. ArtLiber, 2016.
L. A. da Silva, S. M. Peres, and C. Boscarioli, Introdução `a minerção de dados: com aplicações em R. Elsevier Brasil, 2017.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
F. Chollet and J. J. Allaire, Deep Learning With R. Manning Publications, 2018.
L. G. C. Evangelista and E. B. Guedes, “Ensembles of convolutional neural networks on computer-aided pulmonary tuberculosis detection,” IEEE Latin America Transactions, vol. 17, no. 12, pp. 1954–1963, 2019.
O. L. de Sousa, D. M. Magalh˜aes, P. d. A. Vieira, and R. Silva, “Deep learning in image analysis for covid-19 diagnosis: a survey,” IEEE Latin America Transactions, vol. 100, no. 1e, 2020.
F. Pirotti, C. Zanchetta, M. Previtali, and S. Della Torre, “Detection of building roofs and facades from aerial laser scanning data using deep learning,” in 2nd International Conference of Geomatics and Restoration, GEORES 2019, vol. 42, no. 2. Copernicus GmbH, 2019, pp. 975–980.
A. Braun and A. Borrmann, “Combining inverse photogrammetry and bim for automated labeling of construction site images for machine learning,” Automation in Construction, vol. 106, pp. 1–12, 2019.
S. Zhou and W. Song, “Deep learning-based roadway crack classification using laser-scanned range images: A comparative study on hyperparameter selection,” Automation in Construction, vol. 114, 2020.
A. Sawhney, M. Riley, and J. Irizarry, Construction 4.0: An innovation platform for the built environment. Routledge, 2020.
E. Monteiro, M. Oliveira, K. Almeida, J. Carvalho, T. Chaves, and E. ARIMATEIA, “Estudo da degradação nas marquises de edificac¸ ˜oes do centro hist´orico do recife.” in Congresso Internacional sobre Patolog´ıa y Recuperaci´on de Estructuras, 2010.
M. Plaisant, G. Almeida, and A. N. Haddad, “Patologias biol´ogicas– tratamento de vida vegetal nos edif´ıcios hist´oricos do rio de janeiro iv cirmare–rio de janeiro,” IV Congresso Internacional na ”Recuperação, Manutenc¸ ˜ao e Restaurac¸ ˜ao de Edif´ıcios (CIRMARE), 2015.
F. R. de Assunç˜ao Rios, D. D. E. da Silva, J. N. da Costa, and B. J. S. Souza, “An´alise das manifestac¸ ˜oes patol´ogicas das marquises de concreto armado no centro de campina grande-pb,” Revista de Geociˆencias do Nordeste, vol. 5, pp. 12–22, 2019.
M. Kaamin, N. Ahmad, S. Razali, M. Mokhtar, N. Ngadiman, D. Masri, I. Hussin, and L. Asri, “Visual inspection of heritage mosques using unmanned aerial vehicle (uav) and condition survey protocol (csp) 1 matrix: A case study of tengkera mosque and kampung kling mosque, melaka,” vol. 1529, no. 3, 2020.
M. LOUKMA and M. STEFANIDOU, “Causes of deterioration of ottoman mosques,” WIT Transactions on The Built Environment, vol.177, pp. 173–180, 2018.
E. Rocha, J. Macedo, P. Correia, and E. Monteiro, “Adaptation of a damage map to historical buildings with pathological problems: Case study at the church of carmo in olinda, pernambuco,” Revista ALCONPAT, vol. 8, no. 1, pp. 51–63, 2018.
M. L¨angkvist, A. Kiselev, M. Alirezaie, and A. Loutfi, “Classification and segmentation of satellite orthoimagery using convolutional neural networks,” Remote Sensing, vol. 8, no. 4, p. 329, 2016.
G. H¨aufel, L. Lucks, M. Pohl, D. Bulatov, and H. Schilling, “Evaluation of cnns for land cover classification in high-resolution airborne images,” in Earth Resources and Environmental Remote Sensing/GIS Applications IX, vol. 10790. International Society for Optics and Photonics, 2018, p. 1079003.
E. Maltezos, A. Doulamis, N. Doulamis, and C. Ioannidis, “Building extraction from lidar data applying deep convolutional neural networks,” IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 1, pp. 155– 159, 2018.
M. C. Younis and E. Keedwell, “Semantic segmentation on small datasets of satellite images using convolutional neural networks,” Journal of Applied Remote Sensing, vol. 13, no. 4, p. 046510, 2019.
N. Mboga, T. Grippa, S. Georganos, S. Vanhuysse, B. Smets, O. Dewitte, E. Wolff, and M. Lennert, “Fully convolutional networks for land cover classification from historical panchromatic aerial photographs,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 167, pp. 385–395, 2020.
H. Mohammadi and F. Samadzadegan, “An object based framework for building change analysis using 2d and 3d information of high resolution satellite images,” Advances in Space Research, vol. 66, no. 6, pp. 1386– 1404, 2020.
P. Brazdil, C. G. Carrier, C. Soares, and R. Vilalta, Metalearning: Applications to data mining. Springer Science & Business Media, 2009.
F. Hutter, L. Kotthoff, and J. Vanschoren, Eds., Automated Machine Learning: Methods, Systems, Challenges. Springer, 2019, in press, available at http://automl.org/book.
R. G. Mantovani, A. L. Rossi, E. Alcobac¸a, J. Vanschoren, and A. C. de Carvalho, “A meta-learning recommender system for hyperparameter tuning: Predicting when tuning improves svm classifiers,” Information Sciences, vol. 501, pp. 193–221, 2019.
A. L. C. Ottoni, E. G. Nepomuceno, M. S. de Oliveira, and D. C. R. de Oliveira, “Tuning of reinforcement learning parameters applied to sop using the scott–knott method,” Soft Computing, vol. 24, p. 4441–4453, 2020.
C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. J. Cardoso, “Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,” in Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, 2017, pp. 240–248.
M. Kouzehgar, Y. K. Tamilselvam, M. V. Heredia, and M. R. Elara, “Self-reconfigurable fac¸ade-cleaning robot equipped with deep-learningbased crack detection based on convolutional neural networks,” Automation in Construction, vol. 108, p. 102959, 2019.
J. Gim´enez-Gallego, J. D. Gonz´alez-Teruel, M. Jim´enez-Buend´ıa, A. B. Toledo-Moreo, F. Soto-Valles, and R. Torres-S´anchez, “Segmentation of multiple tree leaves pictures with natural backgrounds using deep learning for image-based agriculture applications,” Applied Sciences, vol. 10, no. 1, pp. 1–15, 2020.
A. K. Rangarajan, R. Purushothaman, and A. Ramesh, “Tomato crop disease classification using pre-trained deep learning algorithm,” Procedia computer science, vol. 133, pp. 1040–1047, 2018.
O. Yadav, K. Passi, and C. K. Jain, “Using deep learning to classify x-ray images of potential tuberculosis patients,” in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2018, pp. 2368–2375.
K. Bhosle and V. Musande, “Evaluation of deep learning cnn model for land use land cover classification and crop identification using hyperspectral remote sensing images,” Journal of the Indian Society of Remote Sensing, vol. 47, no. 11, pp. 1949–1958, 2019.
A. Wadhawan and P. Kumar, “Deep learning-based sign language
recognition system for static signs,” Neural Computing and Applications, pp. 1–12, 2020.
S. Postalcıo˘glu, “Performance analysis of different optimizers for deep learning-based image recognition,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 34, no. 02, pp. 1–12, 2020.
A. L. Majdik, C. Till, and D. Scaramuzza, “The zurich urban micro aerial vehicle dataset,” The International Journal of Robotics Research, vol. 36, no. 3, pp. 269–273, 2017.
Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
J. Guo, Q. Wang, Y. Li, and P. Liu, “Fac¸ade defects classification from imbalanced dataset using meta learning-based convolutional neural network,” Computer-Aided Civil and Infrastructure Engineering, 2020.
D. C. Montgomery, Design and analysis of experiments. New York: John Wiley & Sons, 9th, 2017.