A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection
According to the U.S. Department of Transportation, there is an average of six million motor vehicle crashes every year in the United States. For insurance companies, it is very time-consuming and expensive to process claims for detecting and classifying vehicle damages; thus, deep learning techniqu...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LibraryPress@UF
2021-04-01
|
| Series: | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| Online Access: | https://journals.flvc.org/FLAIRS/article/view/128473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849736503723294720 |
|---|---|
| author | Lin Li Koshin Ono Chun-Kit Ngan |
| author_facet | Lin Li Koshin Ono Chun-Kit Ngan |
| author_sort | Lin Li |
| collection | DOAJ |
| description | According to the U.S. Department of Transportation, there is an average of six million motor vehicle crashes every year in the United States. For insurance companies, it is very time-consuming and expensive to process claims for detecting and classifying vehicle damages; thus, deep learning techniques have been used to automate this process to reduce the time and the cost. In this paper, Mask R-CNN is used for image segmentation to identify and crop vehicles from images. Then a convolutional neural network (CNN) model is built to classify whether or not the vehicles have damages. In addition, transfer learning is utilized in both image segmentation and classification phases to help build the models for vehicle detection and damage detection, using the pre-trained weights from Microsoft COCO dataset and ImageNet, respectively. 864 images of damaged vehicles collected from public websites, such as Google Images, are used in this research. The experiment on the detection of bumper damages has achieved 87.5% accuracy. |
| format | Article |
| id | doaj-art-e86687c121ae4d02b1a391b43575e4a6 |
| institution | DOAJ |
| issn | 2334-0754 2334-0762 |
| language | English |
| publishDate | 2021-04-01 |
| publisher | LibraryPress@UF |
| record_format | Article |
| series | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| spelling | doaj-art-e86687c121ae4d02b1a391b43575e4a62025-08-20T03:07:16ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622021-04-013410.32473/flairs.v34i1.12847362867A Deep Learning and Transfer Learning Approach for Vehicle Damage DetectionLin Li0Koshin OnoChun-Kit NganSeattle UniversityAccording to the U.S. Department of Transportation, there is an average of six million motor vehicle crashes every year in the United States. For insurance companies, it is very time-consuming and expensive to process claims for detecting and classifying vehicle damages; thus, deep learning techniques have been used to automate this process to reduce the time and the cost. In this paper, Mask R-CNN is used for image segmentation to identify and crop vehicles from images. Then a convolutional neural network (CNN) model is built to classify whether or not the vehicles have damages. In addition, transfer learning is utilized in both image segmentation and classification phases to help build the models for vehicle detection and damage detection, using the pre-trained weights from Microsoft COCO dataset and ImageNet, respectively. 864 images of damaged vehicles collected from public websites, such as Google Images, are used in this research. The experiment on the detection of bumper damages has achieved 87.5% accuracy.https://journals.flvc.org/FLAIRS/article/view/128473 |
| spellingShingle | Lin Li Koshin Ono Chun-Kit Ngan A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| title | A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection |
| title_full | A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection |
| title_fullStr | A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection |
| title_full_unstemmed | A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection |
| title_short | A Deep Learning and Transfer Learning Approach for Vehicle Damage Detection |
| title_sort | deep learning and transfer learning approach for vehicle damage detection |
| url | https://journals.flvc.org/FLAIRS/article/view/128473 |
| work_keys_str_mv | AT linli adeeplearningandtransferlearningapproachforvehicledamagedetection AT koshinono adeeplearningandtransferlearningapproachforvehicledamagedetection AT chunkitngan adeeplearningandtransferlearningapproachforvehicledamagedetection AT linli deeplearningandtransferlearningapproachforvehicledamagedetection AT koshinono deeplearningandtransferlearningapproachforvehicledamagedetection AT chunkitngan deeplearningandtransferlearningapproachforvehicledamagedetection |