Yol Ağındaki Yapısal Kusurların Küresel Ölçekli Otomatik Yol Kusur Tespit Sistemi İle Belirlenmesi ve Sınıflandırılması
Loading...

Date
2023
Authors
Kaya, Ömer
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Yol ağları farklı üstyapı tasarımları ile oluşturulmaktadır. Genel olarak dünyada en çok kullanılan üstyapı türü olarak esnek kaplama tercih edilmektedir. Bu üstyapıya sahip yol ağları; yol altyapısının hazır olmaması, bitümlü karışımlarda kullanılan bitümün uygulama alanı ile uyumsuzluğu, agrega bitüm oranında yapılan hatalar, döküm sıcaklığı, yetersiz silindir işlemi, kalifiyesiz eleman, mevsimsel değişkenlikler, kar ve buz ile mücadele yöntemleri, trafik hacmi, yetersiz bakım ve onarım süreçleri gibi nedenlerden dolayı bozulmalar yaşamaktadır. Bu bozulmalar zaman içerisinde farklı formlar alarak yol kusurlarını oluşturmaktadır. Kusurların belirlenme süreci yol kaplamasının verimliliği ve trafik bileşenleri için çok önemlidir. Bu tez çalışmasında esnek üst yapılı yol ağlarında meydana gelen yol kusurlarının otomatik olarak belirlenmesi ve sınıflandırılması süreci akıllı bir sistem ile gerçekleştirilmiştir. Sekiz farklı ülkeden elde edilen yol görüntüleri ve 10 farklı yol kusuru çalışma kapsamında dikkate alınmıştır. Kusurlarının algılanma sürecinde YOLOv5, YOLOv7 ve YOLOv8 algılama modelleri kullanılmıştır. Ayrıca farklı ülkelerden oluşan veri seti kapsamında küresel ölçekli otomatik yol kusur belirleme sistemi geliştirilmiştir. Geliştirilen sistemin bir prototip olduğu ve yol ağlarında meydana gelen kusurların gerçek zamanlı olarak algılama ve sınıflama yeteneğine sahiptir. Belirlenen kusurların konum bilgileri de elde edilerek sistemin yol ağı sorumluları için kılavuz olacağı açıktır. Geliştirilen sistem ile yol kusurlarının algılanması, sınıflandırılması ve yerlerinin belirlemesi yol ağlarının bakım ve onarım sürecini hızlandıracağı gibi hizmet ömrünü de uzatacaktır. Yol ağını kullanan trafik bileşenlerinin yol güvenliği ve konforu da artırılmış olacaktır. Sonuç olarak bir akıllı ulaşım sistemleri uygulama biçimi olan araç-altyapı (V2I) iletişim örneği tez kapsamında sunulmuştur.
Road networks are created with different pavement designs. In general, flexible pavement is preferred as the most used superstructure type in the World. Road networks with this superstructure suffers from degradation due to these; due to reasons such as lack of proper road infrastructure, incompatibility of bitumen used in bituminous mixtures with the application area, errors in aggregate bitumen ratio, casting temperature, insufficient roller operation, unqualified personnel, seasonal variations, methods of combating snow and ice, traffic volume, inadequate maintenance and repair processes. These degradations take different forms over time and create road defects. The process of identifying defects is very important for the efficiency of the road pavement and traffic components. In this thesis study, the process of automatic detection and classification of road defects occurring in flexible superstructure road networks was carried out with an intelligent system. Road images obtained from eight different countries and 10 different road defects were taken into consideration within the scope of the study. YOLOv5, YOLOv7 and YOLOv8 detection models were used in the detection process of defects. In addition, a global-scale automatic road defect detection system has been developed within the scope of a data set consisting of different countries. The developed system is a prototype and has the ability to detect and classify defects occurring in road networks in real time. It is clear that the system will be a guide for road network managers by obtaining location information of the identified defects. Detecting, classifying and locating road defects with the developed system will accelerate the maintenance and repair process of road networks and also extend their service life. Road safety and comfort of traffic components using the road network will also be increased. As a result, an example of vehicle-infrastructure (V2I) communication, which is a form of intelligent transportation systems application, is presented within the scope of the thesis.
Road networks are created with different pavement designs. In general, flexible pavement is preferred as the most used superstructure type in the World. Road networks with this superstructure suffers from degradation due to these; due to reasons such as lack of proper road infrastructure, incompatibility of bitumen used in bituminous mixtures with the application area, errors in aggregate bitumen ratio, casting temperature, insufficient roller operation, unqualified personnel, seasonal variations, methods of combating snow and ice, traffic volume, inadequate maintenance and repair processes. These degradations take different forms over time and create road defects. The process of identifying defects is very important for the efficiency of the road pavement and traffic components. In this thesis study, the process of automatic detection and classification of road defects occurring in flexible superstructure road networks was carried out with an intelligent system. Road images obtained from eight different countries and 10 different road defects were taken into consideration within the scope of the study. YOLOv5, YOLOv7 and YOLOv8 detection models were used in the detection process of defects. In addition, a global-scale automatic road defect detection system has been developed within the scope of a data set consisting of different countries. The developed system is a prototype and has the ability to detect and classify defects occurring in road networks in real time. It is clear that the system will be a guide for road network managers by obtaining location information of the identified defects. Detecting, classifying and locating road defects with the developed system will accelerate the maintenance and repair process of road networks and also extend their service life. Road safety and comfort of traffic components using the road network will also be increased. As a result, an example of vehicle-infrastructure (V2I) communication, which is a form of intelligent transportation systems application, is presented within the scope of the thesis.
Description
Keywords
Trafik, Ulaşım, İnşaat Mühendisliği, GIS, Gömülü Desen, Gömülü Sistemler, Sayısal Görüntü İşleme, Video Nesne Bölütlemesi, Traffic, Transportation, Civil Engineering, Embedded Design, Embedded Systems, Digital Image Processing, Video Object Segmentation
Turkish CoHE Thesis Center URL
Fields of Science
Citation
WoS Q
Scopus Q
Source
Volume
Issue
Start Page
End Page
314
