Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.5552/drvind.2022.2108

Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method

Kemal Haciefendioglu ; Karadeniz Technical University, Department of Civil Engineering, Trabzon, Turkey
Hasan Basri Başaga ; Karadeniz Technical University, Department of Civil Engineering, Trabzon, Turkey
Murat Emre Kartal ; İzmir Democracy University, Department of Civil Engineering, İzmir, Turkey
Mehmet Ceyhun Bulut ; Karadeniz Technical University, Department of Civil Engineering, Trabzon, Turkey


Puni tekst: engleski pdf 1.611 Kb

str. 163-176

preuzimanja: 594

citiraj


Sažetak

Wood has a long history of being used as a valuable resource when it comes to building materials. Due to various external factors, in particular the weather, wood is liable to progressive damage over time, which negatively impacts the endurance of wooden structures. Damage assessment is key in understanding, as well as in effectively mitigating, problems that wooden structures are likely to face. The use of a classification system, via deep learning, can potentially reduce the probability of damage in engineering projects reliant on wood. The present study employed a transfer learning technique, to achieve greater accuracy, and instead of training a model from scratch, to determine the likelihood of risks to wooden structures prior to project commencement. Pretrained MobileNet_V2, Inception_V3, and ResNet_V2_50 models were used to customize and initialize weights. A separate set of images, not shown to the trained model, was used to examine the robustness of the models. The three models were compared in their abilities to assess the possibilities and types of damage. Results revealed that all three models achieve performance rates of similar reliability. However, when considering the loss ratios in regard to efficiency, it became apparent that the multi-layered MobileNet_V2 classifier stood out as the most effective of the pre-trained deep convolutional neural network (CNN) models.

Ključne riječi

deep learning method; convolutional neural networks; MobileNet_V2; Inception_V3; ResNet_ V2_50; wooden structures

Hrčak ID:

278445

URI

https://hrcak.srce.hr/278445

Datum izdavanja:

31.5.2022.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.658 *