HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers
Distracted driving causes a large number of traffic accident fatalities and is becoming an increasingly important issue in recent research on traffic safety. Gesture patterns are less distinguishable in vehicles due to in-vehicle physical constraints and body occlusions from the drivers. However, by...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9113267/ |
| _version_ | 1818578001319690240 |
|---|---|
| author | Chen Huang Xiaochen Wang Jiannong Cao Shihui Wang Yan Zhang |
| author_facet | Chen Huang Xiaochen Wang Jiannong Cao Shihui Wang Yan Zhang |
| author_sort | Chen Huang |
| collection | DOAJ |
| description | Distracted driving causes a large number of traffic accident fatalities and is becoming an increasingly important issue in recent research on traffic safety. Gesture patterns are less distinguishable in vehicles due to in-vehicle physical constraints and body occlusions from the drivers. However, by capitalizing on modern camera technology, convolutional neural network (CNN) can be used for visual analysis. In this paper, we present a hybrid CNN framework (HCF) to detect the behaviors of distracted drivers by using deep learning to process image features. To improve the accuracy of the driving activity detection system, we first apply a cooperative pretrained model that combines ResNet50, Inception V3 and Xception to extract driver behavior features based on transfer learning. Second, because the features extracted by pretrained models are independent, we concatenate the extracted features to obtain comprehensive information. Finally, we train the fully connected layers of the HCF to filter out anomalies and hand movements associated with non-distracted driving. We apply an improved dropout algorithm to prevent the proposed HCF from overfitting to the training data. During the evaluation, we apply the class activation mapping (CAM) technique to highlight the feature area involving ten tested classes of typical distracted driving behaviors. The experimental results show that the proposed HCF achieves the classification accuracy of 96.74% when detecting distracted driving behaviors, demonstrating that it can potentially help drivers maintain safe driving habits. |
| first_indexed | 2024-12-16T06:38:52Z |
| format | Article |
| id | doaj.art-2d8059def84140d2b85509750bcea148 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T06:38:52Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2d8059def84140d2b85509750bcea1482022-12-21T22:40:44ZengIEEEIEEE Access2169-35362020-01-01810933510934910.1109/ACCESS.2020.30011599113267HCF: A Hybrid CNN Framework for Behavior Detection of Distracted DriversChen Huang0https://orcid.org/0000-0002-5765-334XXiaochen Wang1https://orcid.org/0000-0002-7974-2802Jiannong Cao2https://orcid.org/0000-0002-2725-2529Shihui Wang3https://orcid.org/0000-0003-2263-1527Yan Zhang4https://orcid.org/0000-0001-7544-6611School of Computer Science and Information Engineering, Hubei University, Wuhan, ChinaSchool of Computer Science and Information Engineering, Hubei University, Wuhan, ChinaDepartment of Computing, The Hong Kong Polytechnic University, Hong KongSchool of Computer Science and Information Engineering, Hubei University, Wuhan, ChinaSchool of Computer Science and Information Engineering, Hubei University, Wuhan, ChinaDistracted driving causes a large number of traffic accident fatalities and is becoming an increasingly important issue in recent research on traffic safety. Gesture patterns are less distinguishable in vehicles due to in-vehicle physical constraints and body occlusions from the drivers. However, by capitalizing on modern camera technology, convolutional neural network (CNN) can be used for visual analysis. In this paper, we present a hybrid CNN framework (HCF) to detect the behaviors of distracted drivers by using deep learning to process image features. To improve the accuracy of the driving activity detection system, we first apply a cooperative pretrained model that combines ResNet50, Inception V3 and Xception to extract driver behavior features based on transfer learning. Second, because the features extracted by pretrained models are independent, we concatenate the extracted features to obtain comprehensive information. Finally, we train the fully connected layers of the HCF to filter out anomalies and hand movements associated with non-distracted driving. We apply an improved dropout algorithm to prevent the proposed HCF from overfitting to the training data. During the evaluation, we apply the class activation mapping (CAM) technique to highlight the feature area involving ten tested classes of typical distracted driving behaviors. The experimental results show that the proposed HCF achieves the classification accuracy of 96.74% when detecting distracted driving behaviors, demonstrating that it can potentially help drivers maintain safe driving habits.https://ieeexplore.ieee.org/document/9113267/Distracted driversconvolutional neural networktransfer learningfusion model |
| spellingShingle | Chen Huang Xiaochen Wang Jiannong Cao Shihui Wang Yan Zhang HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers IEEE Access Distracted drivers convolutional neural network transfer learning fusion model |
| title | HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers |
| title_full | HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers |
| title_fullStr | HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers |
| title_full_unstemmed | HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers |
| title_short | HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers |
| title_sort | hcf a hybrid cnn framework for behavior detection of distracted drivers |
| topic | Distracted drivers convolutional neural network transfer learning fusion model |
| url | https://ieeexplore.ieee.org/document/9113267/ |
| work_keys_str_mv | AT chenhuang hcfahybridcnnframeworkforbehaviordetectionofdistracteddrivers AT xiaochenwang hcfahybridcnnframeworkforbehaviordetectionofdistracteddrivers AT jiannongcao hcfahybridcnnframeworkforbehaviordetectionofdistracteddrivers AT shihuiwang hcfahybridcnnframeworkforbehaviordetectionofdistracteddrivers AT yanzhang hcfahybridcnnframeworkforbehaviordetectionofdistracteddrivers |