AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection
Driver distraction behavior causes a large number of traffic accidents every year, resulting in economic losses and injuries. Currently, the driver still plays an important role in the driving and control of the vehicle due to the low level of vehicle automation and the immature development of auton...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9852210/ |
| _version_ | 1811215084246007808 |
|---|---|
| author | Taiguo Li Yingzhi Zhang Quanqin Li Tiance Zhang |
| author_facet | Taiguo Li Yingzhi Zhang Quanqin Li Tiance Zhang |
| author_sort | Taiguo Li |
| collection | DOAJ |
| description | Driver distraction behavior causes a large number of traffic accidents every year, resulting in economic losses and injuries. Currently, the driver still plays an important role in the driving and control of the vehicle due to the low level of vehicle automation and the immature development of autonomous driving. Therefore, it is vital to research distraction detection for drivers. However, in realistic driving scenarios with uncertain information, they are still some challenges in efficient and accurate driver distraction detection. In this paper, an improved deep learning model based on attention mechanisms and bi-directional feature pyramid networks (BiFPN) is proposed to identify driver distractions. Firstly, an improved data augmentation strategy is introduced to increase the data diversity to enhance the generalization capability of the model. Secondly, the squeeze-and-excitation (SE) attention mechanism layer is used after the C3 module of the original backbone network to enhance the important feature information and suppress the minor feature information. Finally, the BiFPN module is introduced into the neck network to better achieve multi-scale feature fusion without increasing the calculation amount too much. The experimental results show that the method proposed in this paper has an average mean accuracy rate (mAP) of 0.956 on the test set. Compared to the original model the mAP has improved by 13.2%. The detection speed of the model is 71 frames per second, and the memory occupation is 15.9 MB. This method has the advantages of high recognition accuracy, fast detection speed, and small memory occupation of the model, which are important for achieving engineering deployment. |
| first_indexed | 2024-04-12T06:15:25Z |
| format | Article |
| id | doaj.art-dfcda6c2227a431cac03b72431578ac5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T06:15:25Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dfcda6c2227a431cac03b72431578ac52022-12-22T03:44:31ZengIEEEIEEE Access2169-35362022-01-0110831388315110.1109/ACCESS.2022.31971469852210AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior DetectionTaiguo Li0https://orcid.org/0000-0002-0874-4384Yingzhi Zhang1https://orcid.org/0000-0002-6220-0433Quanqin Li2Tiance Zhang3https://orcid.org/0000-0002-4519-4342School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, ChinaSchool of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, ChinaChildren’s Rehabilitation Department, Shaanxi Kangfu Hospital, Xi’an, ChinaSchool of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, ChinaDriver distraction behavior causes a large number of traffic accidents every year, resulting in economic losses and injuries. Currently, the driver still plays an important role in the driving and control of the vehicle due to the low level of vehicle automation and the immature development of autonomous driving. Therefore, it is vital to research distraction detection for drivers. However, in realistic driving scenarios with uncertain information, they are still some challenges in efficient and accurate driver distraction detection. In this paper, an improved deep learning model based on attention mechanisms and bi-directional feature pyramid networks (BiFPN) is proposed to identify driver distractions. Firstly, an improved data augmentation strategy is introduced to increase the data diversity to enhance the generalization capability of the model. Secondly, the squeeze-and-excitation (SE) attention mechanism layer is used after the C3 module of the original backbone network to enhance the important feature information and suppress the minor feature information. Finally, the BiFPN module is introduced into the neck network to better achieve multi-scale feature fusion without increasing the calculation amount too much. The experimental results show that the method proposed in this paper has an average mean accuracy rate (mAP) of 0.956 on the test set. Compared to the original model the mAP has improved by 13.2%. The detection speed of the model is 71 frames per second, and the memory occupation is 15.9 MB. This method has the advantages of high recognition accuracy, fast detection speed, and small memory occupation of the model, which are important for achieving engineering deployment.https://ieeexplore.ieee.org/document/9852210/Driver distractionattention mechanism moduleBiFPN moduledeep convolutional neural networkdriving behavior |
| spellingShingle | Taiguo Li Yingzhi Zhang Quanqin Li Tiance Zhang AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection IEEE Access Driver distraction attention mechanism module BiFPN module deep convolutional neural network driving behavior |
| title | AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection |
| title_full | AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection |
| title_fullStr | AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection |
| title_full_unstemmed | AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection |
| title_short | AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection |
| title_sort | ab dlm an improved deep learning model based on attention mechanism and bifpn for driver distraction behavior detection |
| topic | Driver distraction attention mechanism module BiFPN module deep convolutional neural network driving behavior |
| url | https://ieeexplore.ieee.org/document/9852210/ |
| work_keys_str_mv | AT taiguoli abdlmanimproveddeeplearningmodelbasedonattentionmechanismandbifpnfordriverdistractionbehaviordetection AT yingzhizhang abdlmanimproveddeeplearningmodelbasedonattentionmechanismandbifpnfordriverdistractionbehaviordetection AT quanqinli abdlmanimproveddeeplearningmodelbasedonattentionmechanismandbifpnfordriverdistractionbehaviordetection AT tiancezhang abdlmanimproveddeeplearningmodelbasedonattentionmechanismandbifpnfordriverdistractionbehaviordetection |