FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer | |
Wang, HaiTao3; Chen, Jie1,3; Huang, ZhiXiang3; Li, Bing3; Lv, JianMing3; Xi, JingMin3; Wu, BoCai1; Zhang, Jun2,4; Wu, ZhongCheng2,4 | |
刊名 | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS |
2022-11-10 | |
关键词 | Transformers Vehicles Feature extraction Convolutional neural networks Accidents Roads Convolution Vision transformer distraction detection deep learning residual embedding driving safety |
ISSN号 | 1524-9050 |
DOI | 10.1109/TITS.2022.3219676 |
通讯作者 | Chen, Jie(jiechen@ustc.edu) |
英文摘要 | According to the surveys of the World Health Organization, distracted driving is one of main causes of road traffic accidents. To improve road traffic safety, real-time detection of drivers' driving behavior is very important for the development of highly reliable Advanced Driver Assistance System (ADAS). At present, the deep learning architecture based on a Convolutional Neural Network (CNN) has disadvantages such as large number of parameters and weak global feature extraction ability. Therefore, this paper proposes an innovative driver distraction detection model based on the fusion of a transformer and a CNN, referred to as FPT, which is the first exploration in the field of driver distraction detection. First, we introduce the latest Twins transformer as a benchmark. Then, we design residual embedding to replace block embedding, which can further integrate the convolutional neural network with Transformer and improve the feature extraction ability. In addition, the Multilayer Perceptron (MLP) module with a large parameter occupancy rate in the original transformer structure is replaced with a lightweight group convolution module to reduce computational complexity. Finally, a cross-entropy loss function for label smoothing is designed to guide network learning with significantly differentiated features. Comparison results on two large-scale driver distraction detection datasets show that the proposed FPT offers a better compromise between computational cost and performance compared to the state-of-the-art CNN and Transformer architectures. |
资助项目 | National Natural Science Foundation of China[62001003] ; Natural Science Foundation of Anhui Province[2008085QF284] ; China Postdoctoral Science Foundation[2020M671851] |
WOS关键词 | DRIVING POSTURES ; RECOGNITION |
WOS研究方向 | Engineering ; Transportation |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000881972600001 |
资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Anhui Province ; China Postdoctoral Science Foundation |
内容类型 | 期刊论文 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/130359] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Chen, Jie |
作者单位 | 1.China Elect Technol Grp Corp, Res Inst 38, Hefei 230088, Peoples R China 2.Univ Sci & Technol China, Grad Sch, Hefei 101127, Peoples R China 3.Anhui Univ, Sch Elect & Informat Engn, Informat Mat & Intelligent Sensing Lab Anhui Prov, Key Lab Intelligent Comp & Signal Proc,Minist Edu, Hefei 230601, Peoples R China 4.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 231283, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, HaiTao,Chen, Jie,Huang, ZhiXiang,et al. FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022. |
APA | Wang, HaiTao.,Chen, Jie.,Huang, ZhiXiang.,Li, Bing.,Lv, JianMing.,...&Wu, ZhongCheng.(2022).FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. |
MLA | Wang, HaiTao,et al."FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论