A New Unsupervised Deep Learning Algorithm for Fine-Grained Detection of Driver Distraction
文献类型:期刊论文
作者 | Li, Bing1,2; Chen, Jie1,2,3; Huang, Zhixiang1,2; Wang, Haitao1,2; Lv, Jianming1,2; Xi, Jingmin1,2; Zhang, Jun4,5; Wu, Zhongcheng4,5 |
刊名 | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS |
出版日期 | 2022-04-18 |
ISSN号 | 1524-9050 |
关键词 | Vehicles Accidents Feature extraction Deep learning Data models Convolutional neural networks Computational modeling Unsupervised deep learning driver distraction fine-grained comparative learning stop-gradient multilayer perceptron |
DOI | 10.1109/TITS.2022.3166275 |
通讯作者 | Chen, Jie(jiechen@ustc.edu) |
英文摘要 | Traffic accidents caused by distracted drivers account for a large proportion of traffic accidents each year, and monitoring the driving state of drivers to avoid traffic accidents caused by distracted driving has become a very important research direction. At present, the field of driver distraction detection mainly adopts supervised learning methods, which have problems such as poor generalization ability, large labeling cost, and weak artificial intelligence. This paper is oriented toward driver distraction fine-grained detection and innovatively proposes a new unsupervised deep learning algorithm, which is referred to as UDL, to achieve a more human-like level of intelligence. First, we build a new unsupervised deep learning algorithm; furthermore, we integrate the multilayer perceptron (MLP) architecture to build a new backbone and projection head to strengthen feature extraction capabilities; and finally, a new loss function based on contrast learning and a stop-gradient strategy is designed to guide the model to learn more robust features. The comparison results on large-scale driver distraction detection datasets show that our UDL method can accurately detect driver distraction without labels and exhibits excellent generalization performance with a linear evaluation accuracy of 97.38%; In addition, after fine-tuning with fewer labels, our UDL method can achieve superior performance close to state-of-the-art supervised learning methods, achieving 99.07% accuracy after fine-tuning using only 50% of the labeled data, which greatly reduces the cost and limitations of manual annotation. |
资助项目 | National Natural Science Foundation of China[62001003] ; Natural Science Foundation of Anhui Province[2008085QF284] ; China Postdoctoral Science Foundation[2020M671851] |
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:000785781400001 |
资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Anhui Province ; China Postdoctoral Science Foundation |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/131450] |
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.Anhui Univ, Minist Educ, Informat Mat & Intelligent Sensing Lab Anhui Prov, Hefei 230601, Peoples R China 2.Anhui Univ, Minist Educ, Key Lab Intelligent Comp & Signal Proc, Hefei 230601, Peoples R China 3.China Elect Technol Grp Corp, Res Inst 38, Hefei 230088, Peoples R China 4.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 231283, Peoples R China 5.Univ Sci & Technol China, Grad Sch, Hefei 101127, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Bing,Chen, Jie,Huang, Zhixiang,et al. A New Unsupervised Deep Learning Algorithm for Fine-Grained Detection of Driver Distraction[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022. |
APA | Li, Bing.,Chen, Jie.,Huang, Zhixiang.,Wang, Haitao.,Lv, Jianming.,...&Wu, Zhongcheng.(2022).A New Unsupervised Deep Learning Algorithm for Fine-Grained Detection of Driver Distraction.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. |
MLA | Li, Bing,et al."A New Unsupervised Deep Learning Algorithm for Fine-Grained Detection of Driver Distraction".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022). |
入库方式: OAI收割
来源:合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
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。