However, the literature lacks proposals to optimize the combinations of Data Augmentation hyperparameters for the application of Deep Learning in building construction image classification, especially in the recognition of vegetation on building facades and roofs defects classification. In, different types of Data Augmentation methods were analyzed for crack detection in constructions. In the literature, some studies have analyzed the influence of Data Augmentation hyperparameter combinations in different applications, such as: plant classification, transmission line inspection and covid-19 diagnostic process in chest X-ray radiological imaging. In terms of Machine Learning, this problem can be treated as in the area of Hyperparameter Tuning. In this respect, one of the challenges of using Data Augmentation is the definition of which transformations (such as zoom, rotation, flip) will be applied to the images. This is because, the generation of artificial images directly contributes to increase the capacity for the generalization of the Deep Learning model and thus decrease the chance of overfitting. In fact, Data Augmentation techniques play an important role in the application of Machine Learning in small datasets. verified the improvement in validation accuracy when using Data Augmentation to increase the training database. It is also worth noting that, one of the relevant factors on and was the experiments with Data Augmentation. For example, in a recent study, proposes a methodology to tuning of two hyperparameters (learning rate and optimizer) of Neural Networks in the building roof image classification. In the literature, there are several examples of works that investigated the efficient of roofs structure. Another possibility is to use Deep Learning analysis of roof structures. In this sense, proposes a Deep Learning approach for recognizing vegetation in buildings. In addition, the detection of this pathology in inspection images can assist in the conservation of historic buildings. In fact, the growth of biological manifestations on building facades may indicate the deterioration and degradation of constructions. ĭeep Learning methods can also be applied in recognition of vegetation in building facades images. In recent literature, there are several applications in this research field, such as: crack detection, road crack classification, safety guardrail detection, structural damage recognition, detecting safety helmet, safety harness detection, classification of rock fragments, damage detection of a steel bridge, tunnel lining defects and facade defects classification. In this sense, a possible application of Deep Learning is building construction area. In addition, the hyperparameters recommended by proposed method also achieved the best test results for second case study: \(93.3\%\).ĭeep Learning methods have important applications in the Digital Image Processing field. The results show that the recommended configuration (Height Shift Range = 0.2 Width Shift Range = 0.2 Zoom Range =0.2) reached an accuracy of \(95.6\%\) in the test step of first case study. Experiments were carried out with three architectures of Deep Learning from the literature using the Keras library. In order to do that, Logistic Regression models were used to analyze the performance of Convolutional Neural Networks trained from 128 combinations of transformations in the images. This paper proposes a rigorous methodology for tuning of Data Augmentation hyperparameters in Deep Learning to building construction image classification, especially to vegetation recognition in facades and roofs structure analysis. One challenge of this application is Convolutional Neural Networks adoption in a small datasets. Deep Learning methods have important applications in the building construction image classification field.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |