Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
Road damage seriously affects the comfort and safety of drivers. The detection of road damage is of great importance not only for transportation safety, but also in terms of cost. The detection of road damage is critical for enabling early intervention and repair. In this st...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Firat University
2024-10-01
|
| Series: | Firat University Journal of Experimental and Computational Engineering |
| Online Access: | https://dergipark.org.tr/tr/doi/10.62520/fujece.1421398 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545238281191424 |
|---|---|
| author | Ahmet Cihangir Kavcı Ömer Faruk Cansız |
| author_facet | Ahmet Cihangir Kavcı Ömer Faruk Cansız |
| author_sort | Ahmet Cihangir Kavcı |
| collection | DOAJ |
| description |
Road damage seriously affects the comfort and safety of drivers. The detection of road damage is of great importance not only for transportation safety, but also in terms of cost. The detection of road damage is critical for enabling early intervention and repair. In this study, the road damage detection performance of the YOLO (You Only Look Once) v8 algorithm was evaluated using datasets obtained from different geographies, including Czechia -Türkiye, India-Türkiye, USA-Türkiye, and Japan-Türkiye. The findings revealed both the capabilities of the algorithm in damage detection and the challenges it faced in distinguishing certain types of damage. For the creation of the Türkiye dataset, images of roads in the province of Hatay were recorded. These images were labeled using Microsoft's VoTT application. Comparisons and evaluations were made among the developed models. Among these models, the Japan-Türkiye model yielded the best results with a 0.55 mAP and 0.54 F1 score. The results of the models indicated that the appearance of damage varies according to the geographical location and the quality of road data. It was observed that data consisting of local images and uncertain damage types were important in training. |
| format | Article |
| id | doaj-art-dc5dd3ba78e6437d85a2330b70c493fa |
| institution | Kabale University |
| issn | 2822-2881 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Firat University |
| record_format | Article |
| series | Firat University Journal of Experimental and Computational Engineering |
| spelling | doaj-art-dc5dd3ba78e6437d85a2330b70c493fa2025-01-12T08:01:35ZengFirat UniversityFirat University Journal of Experimental and Computational Engineering2822-28812024-10-013325527010.62520/fujece.1421398 Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye Ahmet Cihangir Kavcı0https://orcid.org/0009-0006-9302-220XÖmer Faruk Cansız1https://orcid.org/0000-0001-6857-2513İSKENDERUN TEKNİK ÜNİVERSİTESİ, MÜHENDİSLİK VE DOĞA BİLİMLERİ FAKÜLTESİ, İNŞAAT MÜHENDİSLİĞİ BÖLÜMÜİSKENDERUN TEKNİK ÜNİVERSİTESİ, MÜHENDİSLİK VE DOĞA BİLİMLERİ FAKÜLTESİ, İNŞAAT MÜHENDİSLİĞİ BÖLÜMÜ Road damage seriously affects the comfort and safety of drivers. The detection of road damage is of great importance not only for transportation safety, but also in terms of cost. The detection of road damage is critical for enabling early intervention and repair. In this study, the road damage detection performance of the YOLO (You Only Look Once) v8 algorithm was evaluated using datasets obtained from different geographies, including Czechia -Türkiye, India-Türkiye, USA-Türkiye, and Japan-Türkiye. The findings revealed both the capabilities of the algorithm in damage detection and the challenges it faced in distinguishing certain types of damage. For the creation of the Türkiye dataset, images of roads in the province of Hatay were recorded. These images were labeled using Microsoft's VoTT application. Comparisons and evaluations were made among the developed models. Among these models, the Japan-Türkiye model yielded the best results with a 0.55 mAP and 0.54 F1 score. The results of the models indicated that the appearance of damage varies according to the geographical location and the quality of road data. It was observed that data consisting of local images and uncertain damage types were important in training.https://dergipark.org.tr/tr/doi/10.62520/fujece.1421398 |
| spellingShingle | Ahmet Cihangir Kavcı Ömer Faruk Cansız Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye Firat University Journal of Experimental and Computational Engineering |
| title |
Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
|
| title_full |
Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
|
| title_fullStr |
Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
|
| title_full_unstemmed |
Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
|
| title_short |
Detection of Road Damages Using Machine Learning Methods with Data Collected from Various Geographies: A Study on Türkiye
|
| title_sort | detection of road damages using machine learning methods with data collected from various geographies a study on turkiye |
| url | https://dergipark.org.tr/tr/doi/10.62520/fujece.1421398 |
| work_keys_str_mv | AT ahmetcihangirkavcı detectionofroaddamagesusingmachinelearningmethodswithdatacollectedfromvariousgeographiesastudyonturkiye AT omerfarukcansız detectionofroaddamagesusingmachinelearningmethodswithdatacollectedfromvariousgeographiesastudyonturkiye |