An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment
The analysis and follow up of asphalt infrastructure using image processing techniques has received increased attention recently. However, the vast majority of developments have focused only on determining the presence or absence of road damages, forgoing other more pressing concerns. Nonetheless, i...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/11/3974 |
| _version_ | 1797565836435652608 |
|---|---|
| author | Gilberto Ochoa-Ruiz Andrés Alonso Angulo-Murillo Alberto Ochoa-Zezzatti Lina María Aguilar-Lobo Juan Antonio Vega-Fernández Shailendra Natraj |
| author_facet | Gilberto Ochoa-Ruiz Andrés Alonso Angulo-Murillo Alberto Ochoa-Zezzatti Lina María Aguilar-Lobo Juan Antonio Vega-Fernández Shailendra Natraj |
| author_sort | Gilberto Ochoa-Ruiz |
| collection | DOAJ |
| description | The analysis and follow up of asphalt infrastructure using image processing techniques has received increased attention recently. However, the vast majority of developments have focused only on determining the presence or absence of road damages, forgoing other more pressing concerns. Nonetheless, in order to be useful to road managers and governmental agencies, the information gathered during an inspection procedure must provide actionable insights that go beyond punctual and isolated measurements: the characteristics, type, and extent of the road damages must be effectively and automatically extracted and digitally stored, preferably using inexpensive mobile equipment. In recent years, computer vision acquisition systems have emerged as a promising solution for road damage automated inspection systems when integrated into georeferenced mobile computing devices such as smartphones. However, the artificial intelligence algorithms that power these computer vision acquisition systems have been rather limited owing to the scarcity of large and homogenized road damage datasets. In this work, we aim to contribute in bridging this gap using two strategies. First, we introduce a new and very large asphalt dataset, which incorporates a set of damages not present in previous studies, making it more robust and representative of certain damages such as potholes. This dataset is composed of 18,345 road damage images captured by a mobile phone mounted on a car, with 45,435 instances of road surface damages (linear, lateral, and alligator cracks; potholes; and various types of painting blurs). In order to generate this dataset, we obtained images from several public datasets and augmented it with crowdsourced images, which where manually annotated for further processing. The images were captured under a variety of weather and illumination conditions and a quality-aware data augmentation strategy was employed to filter out samples of poor quality, which helped in improving the performance metrics over the baseline. Second, we trained different object detection models amenable for mobile implementation with an acceptable performance for many applications. We performed an ablation study to assess the effectiveness of the quality-aware data augmentation strategy and compared our results with other recent works, achieving better accuracies (mAP) for all classes and lower inference times (3× faster). |
| first_indexed | 2024-03-10T19:17:34Z |
| format | Article |
| id | doaj.art-0b8aa8ac6a27476d8048c3230a7ccb1a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:17:34Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0b8aa8ac6a27476d8048c3230a7ccb1a2023-11-20T03:12:11ZengMDPI AGApplied Sciences2076-34172020-06-011011397410.3390/app10113974An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions AssessmentGilberto Ochoa-Ruiz0Andrés Alonso Angulo-Murillo1Alberto Ochoa-Zezzatti2Lina María Aguilar-Lobo3Juan Antonio Vega-Fernández4Shailendra Natraj5Tecnológico de Monterrey, School of Engineering and Sciences, Guadalajara 45201, MexicoMaestría en Cs Computacionales, Universidad Autónoma de Guadalajara, Zapopan 45129, MexicoDoctorado en Tecnología, Universidad Autónoma de Ciudad Juárez, Ciudad Juárez 32315, MexicoMaestría en Cs Computacionales, Universidad Autónoma de Guadalajara, Zapopan 45129, MexicoMaestría en Cs Computacionales, Universidad Autónoma de Guadalajara, Zapopan 45129, MexicoVidrona LTD, Edinburgh HMGP+42, Didcot OX11 0QX, UKThe analysis and follow up of asphalt infrastructure using image processing techniques has received increased attention recently. However, the vast majority of developments have focused only on determining the presence or absence of road damages, forgoing other more pressing concerns. Nonetheless, in order to be useful to road managers and governmental agencies, the information gathered during an inspection procedure must provide actionable insights that go beyond punctual and isolated measurements: the characteristics, type, and extent of the road damages must be effectively and automatically extracted and digitally stored, preferably using inexpensive mobile equipment. In recent years, computer vision acquisition systems have emerged as a promising solution for road damage automated inspection systems when integrated into georeferenced mobile computing devices such as smartphones. However, the artificial intelligence algorithms that power these computer vision acquisition systems have been rather limited owing to the scarcity of large and homogenized road damage datasets. In this work, we aim to contribute in bridging this gap using two strategies. First, we introduce a new and very large asphalt dataset, which incorporates a set of damages not present in previous studies, making it more robust and representative of certain damages such as potholes. This dataset is composed of 18,345 road damage images captured by a mobile phone mounted on a car, with 45,435 instances of road surface damages (linear, lateral, and alligator cracks; potholes; and various types of painting blurs). In order to generate this dataset, we obtained images from several public datasets and augmented it with crowdsourced images, which where manually annotated for further processing. The images were captured under a variety of weather and illumination conditions and a quality-aware data augmentation strategy was employed to filter out samples of poor quality, which helped in improving the performance metrics over the baseline. Second, we trained different object detection models amenable for mobile implementation with an acceptable performance for many applications. We performed an ablation study to assess the effectiveness of the quality-aware data augmentation strategy and compared our results with other recent works, achieving better accuracies (mAP) for all classes and lower inference times (3× faster).https://www.mdpi.com/2076-3417/10/11/3974asphalt damagedatasetdeep learningobject detectionasset management |
| spellingShingle | Gilberto Ochoa-Ruiz Andrés Alonso Angulo-Murillo Alberto Ochoa-Zezzatti Lina María Aguilar-Lobo Juan Antonio Vega-Fernández Shailendra Natraj An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment Applied Sciences asphalt damage dataset deep learning object detection asset management |
| title | An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment |
| title_full | An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment |
| title_fullStr | An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment |
| title_full_unstemmed | An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment |
| title_short | An Asphalt Damage Dataset and Detection System Based on RetinaNet for Road Conditions Assessment |
| title_sort | asphalt damage dataset and detection system based on retinanet for road conditions assessment |
| topic | asphalt damage dataset deep learning object detection asset management |
| url | https://www.mdpi.com/2076-3417/10/11/3974 |
| work_keys_str_mv | AT gilbertoochoaruiz anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT andresalonsoangulomurillo anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT albertoochoazezzatti anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT linamariaaguilarlobo anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT juanantoniovegafernandez anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT shailendranatraj anasphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT gilbertoochoaruiz asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT andresalonsoangulomurillo asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT albertoochoazezzatti asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT linamariaaguilarlobo asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT juanantoniovegafernandez asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment AT shailendranatraj asphaltdamagedatasetanddetectionsystembasedonretinanetforroadconditionsassessment |