Real-Time Driver Behavior Detection Based on Deep Deformable Inverted Residual Network With an Attention Mechanism for Human-Vehicle Co-Driving System
Author:
Affiliation:
1. School of Automobile, Chang'an University, Xi'an, China
2. School of Automotive and Traffic Engineering, Hubei University of Arts and Science, Xiangyang, China
Funder
National Key R&D Program of China
Scientific Innovation Practice Project of Postgraduates of Chang'an University
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Aerospace Engineering,Automotive Engineering
Link
http://xplorestaging.ieee.org/ielx7/25/9990993/09847058.pdf?arnumber=9847058
Reference46 articles.
1. Mish: A self regularized non-monotonic activation function;misra,0
2. Batch normalization: Accelerating deep network training by reducing internal covariate shift;ioffe;Proc 32nd Int Conf Mach Learn,0
3. MobileNets: Efficient convolutional neural networks for mobile vision applications;howard,0
4. Identity mappings in deep residual networks;he;Computer Vision—ECCV 2016 (Lecture Notes in Computer Science 8808),2016
5. Densely Connected Convolutional Networks
Cited by 13 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Deep learning for cross-domain data fusion in urban computing: Taxonomy, advances, and outlook;Information Fusion;2025-01
2. LGD-FCOS: driver distraction detection using improved FCOS based on local and global knowledge distillation;Journal of Electronic Imaging;2024-08-16
3. Data-Driven Multi-Dimension Driving Safety Evaluation for Real-World Electric Vehicles;IEEE Transactions on Vehicular Technology;2024-07
4. Human–Machine Shared Control for Path Following Considering Driver Fatigue Characteristics;IEEE Transactions on Intelligent Transportation Systems;2024-07
5. Distraction-level recognition based on stacking ensemble learning for IVIS secondary tasks;Expert Systems with Applications;2024-06
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3