A Data Augmentation Approach to Distracted Driving Detection
Distracted driving behavior has become a leading cause of vehicle crashes. This paper proposes a data augmentation method for distracted driving detection based on the driving operation area. First, the class activation mapping method is used to show the key feature areas of driving behavior analysi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/13/1/1 |
| _version_ | 1798031879420510208 |
|---|---|
| author | Jing Wang ZhongCheng Wu Fang Li Jun Zhang |
| author_facet | Jing Wang ZhongCheng Wu Fang Li Jun Zhang |
| author_sort | Jing Wang |
| collection | DOAJ |
| description | Distracted driving behavior has become a leading cause of vehicle crashes. This paper proposes a data augmentation method for distracted driving detection based on the driving operation area. First, the class activation mapping method is used to show the key feature areas of driving behavior analysis, and then the driving operation areas are detected by the faster R-CNN detection model for data augmentation. Finally, the convolutional neural network classification mode is implemented and evaluated to detect the original dataset and the driving operation area dataset. The classification result achieves a 96.97% accuracy using the distracted driving dataset. The results show the necessity of driving operation area extraction in the preprocessing stage, which can effectively remove the redundant information in the images to get a higher classification accuracy rate. The method of this research can be used to detect drivers in actual application scenarios to identify dangerous driving behaviors, which helps to give early warning of unsafe driving behaviors and avoid accidents. |
| first_indexed | 2024-04-11T20:04:50Z |
| format | Article |
| id | doaj.art-86577b33ce2e45b588a43a32a1f53350 |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-04-11T20:04:50Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-86577b33ce2e45b588a43a32a1f533502022-12-22T04:05:22ZengMDPI AGFuture Internet1999-59032020-12-01131110.3390/fi13010001A Data Augmentation Approach to Distracted Driving DetectionJing Wang0ZhongCheng Wu1Fang Li2Jun Zhang3High Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHigh Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHigh Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHigh Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaDistracted driving behavior has become a leading cause of vehicle crashes. This paper proposes a data augmentation method for distracted driving detection based on the driving operation area. First, the class activation mapping method is used to show the key feature areas of driving behavior analysis, and then the driving operation areas are detected by the faster R-CNN detection model for data augmentation. Finally, the convolutional neural network classification mode is implemented and evaluated to detect the original dataset and the driving operation area dataset. The classification result achieves a 96.97% accuracy using the distracted driving dataset. The results show the necessity of driving operation area extraction in the preprocessing stage, which can effectively remove the redundant information in the images to get a higher classification accuracy rate. The method of this research can be used to detect drivers in actual application scenarios to identify dangerous driving behaviors, which helps to give early warning of unsafe driving behaviors and avoid accidents.https://www.mdpi.com/1999-5903/13/1/1distracted drivingdriving behaviordriving operation areadata augmentationfeature extraction |
| spellingShingle | Jing Wang ZhongCheng Wu Fang Li Jun Zhang A Data Augmentation Approach to Distracted Driving Detection Future Internet distracted driving driving behavior driving operation area data augmentation feature extraction |
| title | A Data Augmentation Approach to Distracted Driving Detection |
| title_full | A Data Augmentation Approach to Distracted Driving Detection |
| title_fullStr | A Data Augmentation Approach to Distracted Driving Detection |
| title_full_unstemmed | A Data Augmentation Approach to Distracted Driving Detection |
| title_short | A Data Augmentation Approach to Distracted Driving Detection |
| title_sort | data augmentation approach to distracted driving detection |
| topic | distracted driving driving behavior driving operation area data augmentation feature extraction |
| url | https://www.mdpi.com/1999-5903/13/1/1 |
| work_keys_str_mv | AT jingwang adataaugmentationapproachtodistracteddrivingdetection AT zhongchengwu adataaugmentationapproachtodistracteddrivingdetection AT fangli adataaugmentationapproachtodistracteddrivingdetection AT junzhang adataaugmentationapproachtodistracteddrivingdetection AT jingwang dataaugmentationapproachtodistracteddrivingdetection AT zhongchengwu dataaugmentationapproachtodistracteddrivingdetection AT fangli dataaugmentationapproachtodistracteddrivingdetection AT junzhang dataaugmentationapproachtodistracteddrivingdetection |