Driver behaviour recognition based on recursive all‐pair field transform time series model
Abstract To standardize driver behaviour and enhance transportation system safety, a dynamic driver behaviour recognition method based on the Recurrent All‐Pairs Field Transforms (RAFT) temporal model is proposed. This study involves the creation of two datasets, namely, Driver‐img and Driver‐vid, i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-09-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/itr2.12528 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846164018424709120 |
|---|---|
| author | HuiZhi Xu ZhaoHao Xing YongShuai Ge DongSheng Hao MengYing Chang |
| author_facet | HuiZhi Xu ZhaoHao Xing YongShuai Ge DongSheng Hao MengYing Chang |
| author_sort | HuiZhi Xu |
| collection | DOAJ |
| description | Abstract To standardize driver behaviour and enhance transportation system safety, a dynamic driver behaviour recognition method based on the Recurrent All‐Pairs Field Transforms (RAFT) temporal model is proposed. This study involves the creation of two datasets, namely, Driver‐img and Driver‐vid, including driver behaviour images and videos across various scenarios. These datasets are subject to preprocessing using RAFT optical flow techniques to enhance the cognitive process of the network. This approach employs a two‐stage temporal model for driver behaviour recognition. In the initial stage, the MobileNet network is optimized and the GYY module is introduced, which includes residuals and global average pooling layers, thereby enhancing the network's feature extraction capabilities. In the subsequent stage, a bidirectional GRU network is constructed to learn driver behaviour video features with temporal information. Additionally, a method for compressing and padding video frames is proposed, which serves as input to the GRU network and enables intent prediction 0.2 s prior to driver actions. Model performance is assessed through accuracy, recall, and F1 score, with experimental results indicating that RAFT preprocessing enhances accuracy, reduces training time, and improves overall model stability, facilitating the recognition of driver behaviour intent. |
| format | Article |
| id | doaj-art-ddb98f21967a4c719a7f91a6e4242c23 |
| institution | Kabale University |
| issn | 1751-956X 1751-9578 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj-art-ddb98f21967a4c719a7f91a6e4242c232024-11-18T16:53:17ZengWileyIET Intelligent Transport Systems1751-956X1751-95782024-09-011891559157310.1049/itr2.12528Driver behaviour recognition based on recursive all‐pair field transform time series modelHuiZhi Xu0ZhaoHao Xing1YongShuai Ge2DongSheng Hao3MengYing Chang4School of Civil Engineering and Transportation Northeast Forestry University Harbin Heilongjiang ChinaSchool of Civil Engineering and Transportation Northeast Forestry University Harbin Heilongjiang ChinaSchool of Civil Engineering and Transportation Northeast Forestry University Harbin Heilongjiang ChinaSchool of Civil Engineering and Transportation Northeast Forestry University Harbin Heilongjiang ChinaSchool of Civil Engineering and Transportation Northeast Forestry University Harbin Heilongjiang ChinaAbstract To standardize driver behaviour and enhance transportation system safety, a dynamic driver behaviour recognition method based on the Recurrent All‐Pairs Field Transforms (RAFT) temporal model is proposed. This study involves the creation of two datasets, namely, Driver‐img and Driver‐vid, including driver behaviour images and videos across various scenarios. These datasets are subject to preprocessing using RAFT optical flow techniques to enhance the cognitive process of the network. This approach employs a two‐stage temporal model for driver behaviour recognition. In the initial stage, the MobileNet network is optimized and the GYY module is introduced, which includes residuals and global average pooling layers, thereby enhancing the network's feature extraction capabilities. In the subsequent stage, a bidirectional GRU network is constructed to learn driver behaviour video features with temporal information. Additionally, a method for compressing and padding video frames is proposed, which serves as input to the GRU network and enables intent prediction 0.2 s prior to driver actions. Model performance is assessed through accuracy, recall, and F1 score, with experimental results indicating that RAFT preprocessing enhances accuracy, reduces training time, and improves overall model stability, facilitating the recognition of driver behaviour intent.https://doi.org/10.1049/itr2.12528computer visionconvolutional neural netsintelligent transportation systemsmanagement and controlroad traffictraffic modelling |
| spellingShingle | HuiZhi Xu ZhaoHao Xing YongShuai Ge DongSheng Hao MengYing Chang Driver behaviour recognition based on recursive all‐pair field transform time series model IET Intelligent Transport Systems computer vision convolutional neural nets intelligent transportation systems management and control road traffic traffic modelling |
| title | Driver behaviour recognition based on recursive all‐pair field transform time series model |
| title_full | Driver behaviour recognition based on recursive all‐pair field transform time series model |
| title_fullStr | Driver behaviour recognition based on recursive all‐pair field transform time series model |
| title_full_unstemmed | Driver behaviour recognition based on recursive all‐pair field transform time series model |
| title_short | Driver behaviour recognition based on recursive all‐pair field transform time series model |
| title_sort | driver behaviour recognition based on recursive all pair field transform time series model |
| topic | computer vision convolutional neural nets intelligent transportation systems management and control road traffic traffic modelling |
| url | https://doi.org/10.1049/itr2.12528 |
| work_keys_str_mv | AT huizhixu driverbehaviourrecognitionbasedonrecursiveallpairfieldtransformtimeseriesmodel AT zhaohaoxing driverbehaviourrecognitionbasedonrecursiveallpairfieldtransformtimeseriesmodel AT yongshuaige driverbehaviourrecognitionbasedonrecursiveallpairfieldtransformtimeseriesmodel AT dongshenghao driverbehaviourrecognitionbasedonrecursiveallpairfieldtransformtimeseriesmodel AT mengyingchang driverbehaviourrecognitionbasedonrecursiveallpairfieldtransformtimeseriesmodel |