ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING
Rock mass discontinuity and orientation are among the important rock mass features. They are conventionally determined with scan-line surveys by engineering geologists in field, which can be difficult or impossible depending on site accessibility. Photogrammetry and computer vision techniques can ai...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-08-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/609/2023/isprs-archives-XLVIII-M-1-2023-609-2023.pdf |
| _version_ | 1797743042602467328 |
|---|---|
| author | I. Yalcin I. Yalcin R. Can R. Can S. Kocaman C. Gokceoglu |
| author_facet | I. Yalcin I. Yalcin R. Can R. Can S. Kocaman C. Gokceoglu |
| author_sort | I. Yalcin |
| collection | DOAJ |
| description | Rock mass discontinuity and orientation are among the important rock mass features. They are conventionally determined with scan-line surveys by engineering geologists in field, which can be difficult or impossible depending on site accessibility. Photogrammetry and computer vision techniques can aid to automatically perform these measurements, although variations in size, shape and appearance of rock masses make the task challenging. Here we propose an automated approach for the detection of rock mass discontinuities using deep learning and photogrammetric image processing methods. Two deep convolutional neural network (DCNNs) were implemented for this purpose and applied to basalts in Kizilcahamam Guvem Geosite near Ankara, Türkiye. Red-green-blue (RGB) band images of the site were taken from an off-the-shelf camera with 1.7 mm resolution and a 3D digital surface model and orthophotos were produced by using photogrammetric software. The discontinuities were delineated manually on the orthophoto and converted to masks. The first DCNN model was based on the open-source crack dataset consisting of a total of 11,298 road and pavement images, which were used to train the Resnet-18 model (Model-1). The second model (Model-2) was based on fine-tuning of Model-1 using the study data from Kizilcahamam. After fine-tuning, Model-2 was able to achieve high performance with a Jaccard Score of 88% on the test data. The results show high potential of the methodology for transfer learning with fine-tuning of a small amount of data that can be applied to other sites and rock mass types as well. |
| first_indexed | 2024-03-12T14:49:51Z |
| format | Article |
| id | doaj.art-86e27bc9635540fca16c067bc43452a4 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-03-12T14:49:51Z |
| publishDate | 2023-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-86e27bc9635540fca16c067bc43452a42023-08-15T17:01:13ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342023-08-01XLVIII-M-1-202360961410.5194/isprs-archives-XLVIII-M-1-2023-609-2023ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNINGI. Yalcin0I. Yalcin1R. Can2R. Can3S. Kocaman4C. Gokceoglu5Hacettepe University, Graduate School of Science and Engineering, Beytepe, Ankara, TürkiyeHacettepe University, Başkent OSB Technical Sciences Vocational School, 06909 Sincan Ankara, TürkiyeHacettepe University, Dept. of Geomatics Engineering, 06800 Beytepe Ankara, TürkiyeTÜBİTAK, Space Technologies Research Institute, 06800, METU Campus, Ankara, TürkiyeHacettepe University, Dept. of Geomatics Engineering, 06800 Beytepe Ankara, TürkiyeHacettepe University, Dept. of Geological Engineering, 06800 Beytepe Ankara, TürkiyeRock mass discontinuity and orientation are among the important rock mass features. They are conventionally determined with scan-line surveys by engineering geologists in field, which can be difficult or impossible depending on site accessibility. Photogrammetry and computer vision techniques can aid to automatically perform these measurements, although variations in size, shape and appearance of rock masses make the task challenging. Here we propose an automated approach for the detection of rock mass discontinuities using deep learning and photogrammetric image processing methods. Two deep convolutional neural network (DCNNs) were implemented for this purpose and applied to basalts in Kizilcahamam Guvem Geosite near Ankara, Türkiye. Red-green-blue (RGB) band images of the site were taken from an off-the-shelf camera with 1.7 mm resolution and a 3D digital surface model and orthophotos were produced by using photogrammetric software. The discontinuities were delineated manually on the orthophoto and converted to masks. The first DCNN model was based on the open-source crack dataset consisting of a total of 11,298 road and pavement images, which were used to train the Resnet-18 model (Model-1). The second model (Model-2) was based on fine-tuning of Model-1 using the study data from Kizilcahamam. After fine-tuning, Model-2 was able to achieve high performance with a Jaccard Score of 88% on the test data. The results show high potential of the methodology for transfer learning with fine-tuning of a small amount of data that can be applied to other sites and rock mass types as well.https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/609/2023/isprs-archives-XLVIII-M-1-2023-609-2023.pdf |
| spellingShingle | I. Yalcin I. Yalcin R. Can R. Can S. Kocaman C. Gokceoglu ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING |
| title_full | ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING |
| title_fullStr | ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING |
| title_full_unstemmed | ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING |
| title_short | ROCK MASS DISCONTINUITY DETERMINATION WITH TRANSFER LEARNING |
| title_sort | rock mass discontinuity determination with transfer learning |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/609/2023/isprs-archives-XLVIII-M-1-2023-609-2023.pdf |
| work_keys_str_mv | AT iyalcin rockmassdiscontinuitydeterminationwithtransferlearning AT iyalcin rockmassdiscontinuitydeterminationwithtransferlearning AT rcan rockmassdiscontinuitydeterminationwithtransferlearning AT rcan rockmassdiscontinuitydeterminationwithtransferlearning AT skocaman rockmassdiscontinuitydeterminationwithtransferlearning AT cgokceoglu rockmassdiscontinuitydeterminationwithtransferlearning |