Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites
The objective of this study is to evaluate the feasibility of deep-learning-based segmentation of the area covered by fresh and young concrete in the images of construction sites. The RGB images of construction sites under various actual situations were used as an input into several types of convolu...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/dbb90e7b4f8141928b753b35681c22d5 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:dbb90e7b4f8141928b753b35681c22d5 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:dbb90e7b4f8141928b753b35681c22d52021-11-11T17:52:57ZDeep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites10.3390/ma142163111996-1944https://doaj.org/article/dbb90e7b4f8141928b753b35681c22d52021-10-01T00:00:00Zhttps://www.mdpi.com/1996-1944/14/21/6311https://doaj.org/toc/1996-1944The objective of this study is to evaluate the feasibility of deep-learning-based segmentation of the area covered by fresh and young concrete in the images of construction sites. The RGB images of construction sites under various actual situations were used as an input into several types of convolutional neural network (CNN)–based segmentation models, which were trained using training image sets. Various ranges of threshold values were applied for the classification, and their accuracy and recall capacity were quantified. The trained models could segment the concrete area overall although they were not able to judge the difference between concrete of different ages as professionals can. By increasing the threshold values for the softmax classifier, the cases of incorrect prediction as concrete became almost zero, while some areas of concrete became segmented as not concrete.Woldeamanuel Minwuye MesfinSoojin ChoJeongmin LeeHyeong-Ki KimTaehoon KimMDPI AGarticleconcretesectionconstruction sitedeep learningconvolutional neural network (CNN)image segmentationTechnologyTElectrical engineering. Electronics. Nuclear engineeringTK1-9971Engineering (General). Civil engineering (General)TA1-2040MicroscopyQH201-278.5Descriptive and experimental mechanicsQC120-168.85ENMaterials, Vol 14, Iss 6311, p 6311 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
concrete section construction site deep learning convolutional neural network (CNN) image segmentation Technology T Electrical engineering. Electronics. Nuclear engineering TK1-9971 Engineering (General). Civil engineering (General) TA1-2040 Microscopy QH201-278.5 Descriptive and experimental mechanics QC120-168.85 |
| spellingShingle |
concrete section construction site deep learning convolutional neural network (CNN) image segmentation Technology T Electrical engineering. Electronics. Nuclear engineering TK1-9971 Engineering (General). Civil engineering (General) TA1-2040 Microscopy QH201-278.5 Descriptive and experimental mechanics QC120-168.85 Woldeamanuel Minwuye Mesfin Soojin Cho Jeongmin Lee Hyeong-Ki Kim Taehoon Kim Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| description |
The objective of this study is to evaluate the feasibility of deep-learning-based segmentation of the area covered by fresh and young concrete in the images of construction sites. The RGB images of construction sites under various actual situations were used as an input into several types of convolutional neural network (CNN)–based segmentation models, which were trained using training image sets. Various ranges of threshold values were applied for the classification, and their accuracy and recall capacity were quantified. The trained models could segment the concrete area overall although they were not able to judge the difference between concrete of different ages as professionals can. By increasing the threshold values for the softmax classifier, the cases of incorrect prediction as concrete became almost zero, while some areas of concrete became segmented as not concrete. |
| format |
article |
| author |
Woldeamanuel Minwuye Mesfin Soojin Cho Jeongmin Lee Hyeong-Ki Kim Taehoon Kim |
| author_facet |
Woldeamanuel Minwuye Mesfin Soojin Cho Jeongmin Lee Hyeong-Ki Kim Taehoon Kim |
| author_sort |
Woldeamanuel Minwuye Mesfin |
| title |
Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| title_short |
Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| title_full |
Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| title_fullStr |
Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| title_full_unstemmed |
Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites |
| title_sort |
deep-learning-based segmentation of fresh or young concrete sections from images of construction sites |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/dbb90e7b4f8141928b753b35681c22d5 |
| work_keys_str_mv |
AT woldeamanuelminwuyemesfin deeplearningbasedsegmentationoffreshoryoungconcretesectionsfromimagesofconstructionsites AT soojincho deeplearningbasedsegmentationoffreshoryoungconcretesectionsfromimagesofconstructionsites AT jeongminlee deeplearningbasedsegmentationoffreshoryoungconcretesectionsfromimagesofconstructionsites AT hyeongkikim deeplearningbasedsegmentationoffreshoryoungconcretesectionsfromimagesofconstructionsites AT taehoonkim deeplearningbasedsegmentationoffreshoryoungconcretesectionsfromimagesofconstructionsites |
| _version_ |
1718432030075650048 |