Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach
Road authorities worldwide can leverage the advances in vehicle technology by continuously monitoring their roads’ conditions to minimize road maintenance costs. The existing methods for carrying out road condition surveys involve manual observations using standard survey forms, performed by qualifi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Vehicles |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-8921/5/3/51 |
| _version_ | 1797576496324280320 |
|---|---|
| author | Cuthbert Ruseruka Judith Mwakalonge Gurcan Comert Saidi Siuhi Judy Perkins |
| author_facet | Cuthbert Ruseruka Judith Mwakalonge Gurcan Comert Saidi Siuhi Judy Perkins |
| author_sort | Cuthbert Ruseruka |
| collection | DOAJ |
| description | Road authorities worldwide can leverage the advances in vehicle technology by continuously monitoring their roads’ conditions to minimize road maintenance costs. The existing methods for carrying out road condition surveys involve manual observations using standard survey forms, performed by qualified personnel. These methods are expensive, time-consuming, infrequent, and can hardly provide real-time information. Some automated approaches also exist but are very expensive since they require special vehicles equipped with computing devices and sensors for data collection and processing. This research aims to leverage the advances in vehicle technology in providing a cheap and real-time approach to carry out road condition monitoring (RCM). This study developed a deep learning model using the You Only Look Once, Version 5 (YOLOv5) algorithm that was trained to capture and categorize flexible pavement distresses (FPD) and reached 95% precision, 93.4% recall, and 97.2% mean Average Precision. Using vehicle built-in cameras and GPS sensors, these distresses were detected, images were captured, and locations were recorded. This was validated on campus roads and parking lots using a car featured with a built-in camera and GPS. The vehicles’ built-in technologies provided a more cost-effective and efficient road condition monitoring approach that could also provide real-time road conditions. |
| first_indexed | 2024-03-10T21:52:45Z |
| format | Article |
| id | doaj.art-a16f335149c8472295465c7c3add7d51 |
| institution | Directory Open Access Journal |
| issn | 2624-8921 |
| language | English |
| last_indexed | 2024-03-10T21:52:45Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Vehicles |
| spelling | doaj.art-a16f335149c8472295465c7c3add7d512023-11-19T13:20:09ZengMDPI AGVehicles2624-89212023-08-015393194810.3390/vehicles5030051Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning ApproachCuthbert Ruseruka0Judith Mwakalonge1Gurcan Comert2Saidi Siuhi3Judy Perkins4Department of Engineering, South Carolina State University, Orangeburg, SC 29117, USADepartment of Engineering, South Carolina State University, Orangeburg, SC 29117, USAComputer Science, Physics, and Engineering Department, Benedict College, 1600 Harden St, Columbia, SC 29204, USADepartment of Engineering, South Carolina State University, Orangeburg, SC 29117, USADepartment of Engineering, Prairie View A&M University (PVAMU), 700 University Drive, Prairie View, TX 77446, USARoad authorities worldwide can leverage the advances in vehicle technology by continuously monitoring their roads’ conditions to minimize road maintenance costs. The existing methods for carrying out road condition surveys involve manual observations using standard survey forms, performed by qualified personnel. These methods are expensive, time-consuming, infrequent, and can hardly provide real-time information. Some automated approaches also exist but are very expensive since they require special vehicles equipped with computing devices and sensors for data collection and processing. This research aims to leverage the advances in vehicle technology in providing a cheap and real-time approach to carry out road condition monitoring (RCM). This study developed a deep learning model using the You Only Look Once, Version 5 (YOLOv5) algorithm that was trained to capture and categorize flexible pavement distresses (FPD) and reached 95% precision, 93.4% recall, and 97.2% mean Average Precision. Using vehicle built-in cameras and GPS sensors, these distresses were detected, images were captured, and locations were recorded. This was validated on campus roads and parking lots using a car featured with a built-in camera and GPS. The vehicles’ built-in technologies provided a more cost-effective and efficient road condition monitoring approach that could also provide real-time road conditions.https://www.mdpi.com/2624-8921/5/3/51pavement distressesroad condition monitoringdeep learning in road damage detectionbuilt-in vehicle camerasGPS sensors in road condition monitoringpavement damage detection using deep learning |
| spellingShingle | Cuthbert Ruseruka Judith Mwakalonge Gurcan Comert Saidi Siuhi Judy Perkins Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach Vehicles pavement distresses road condition monitoring deep learning in road damage detection built-in vehicle cameras GPS sensors in road condition monitoring pavement damage detection using deep learning |
| title | Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach |
| title_full | Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach |
| title_fullStr | Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach |
| title_full_unstemmed | Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach |
| title_short | Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach |
| title_sort | road condition monitoring using vehicle built in cameras and gps sensors a deep learning approach |
| topic | pavement distresses road condition monitoring deep learning in road damage detection built-in vehicle cameras GPS sensors in road condition monitoring pavement damage detection using deep learning |
| url | https://www.mdpi.com/2624-8921/5/3/51 |
| work_keys_str_mv | AT cuthbertruseruka roadconditionmonitoringusingvehiclebuiltincamerasandgpssensorsadeeplearningapproach AT judithmwakalonge roadconditionmonitoringusingvehiclebuiltincamerasandgpssensorsadeeplearningapproach AT gurcancomert roadconditionmonitoringusingvehiclebuiltincamerasandgpssensorsadeeplearningapproach AT saidisiuhi roadconditionmonitoringusingvehiclebuiltincamerasandgpssensorsadeeplearningapproach AT judyperkins roadconditionmonitoringusingvehiclebuiltincamerasandgpssensorsadeeplearningapproach |