中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地质与地球物理研究所
  3. 中国科学院地质与地球物理研究所
A Refined Non-Driving Activity Classification Using a Two-Stream Convolutional Neural Network

文献类型：期刊论文

作者Yang, Lichao4; Yang, Ting-Yu3; Liu, Haochen4; Shan, Xiaocai2; Brighton, James4; Skrypchuk, Lee1; Mouzakitis, Alexandros1; Zhao, Yifan4
刊名IEEE SENSORS JOURNAL
出版日期2021-07-15
卷号21期号:14页码:15574-15583
关键词NDA classification Level 3 automation optical flow 2-stream CNN
ISSN号1530-437X
DOI10.1109/JSEN.2020.3005810
英文摘要It is of great importance to monitor the driver's status to achieve an intelligent and safe take-over transition in the level 3 automated driving vehicle. We present a camera-based system to recognise the non-driving activities (NDAs) which may lead to different cognitive capabilities for take-over based on a fusion of spatial and temporal information. The region of interest (ROI) is automatically selected based on the extracted masks of the driver and the object/device interacting with. Then, the RGB image of the ROI (the spatial stream) and its associated current and historical optical flow frames (the temporal stream) are fed into a two-stream convolutional neural network (CNN) for the classification of NDAs. Such an approach is able to identify not only the object/device but also the interaction mode between the object and the driver, which enables a refined NDA classification. In this paper, we evaluated the performance of classifying 10 NDAs with two types of devices (tablet and phone) and 5 types of tasks (emailing, reading, watching videos, web-browsing and gaming) for 10 participants. Results show that the proposed system improves the averaged classification accuracy from 61.0% when using a single spatial stream to 90.5%.
WOS关键词RECOGNITION
资助项目Jaguar Land Rover ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme[EP/N012089/1] ; Cranfield's EPSRC Impact Accrelate Account[EP/R511511/1]
WOS研究方向Engineering ; Instruments & Instrumentation ; Physics
语种英语
WOS记录号WOS:000673632700007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Jaguar Land Rover ; Jaguar Land Rover ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; Cranfield's EPSRC Impact Accrelate Account ; Cranfield's EPSRC Impact Accrelate Account ; Jaguar Land Rover ; Jaguar Land Rover ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; Cranfield's EPSRC Impact Accrelate Account ; Cranfield's EPSRC Impact Accrelate Account ; Jaguar Land Rover ; Jaguar Land Rover ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; Cranfield's EPSRC Impact Accrelate Account ; Cranfield's EPSRC Impact Accrelate Account ; Jaguar Land Rover ; Jaguar Land Rover ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; U.K.-EPSRC through the Towards Autonomy: Smart and Connected Control (TASCC) Programme ; Cranfield's EPSRC Impact Accrelate Account ; Cranfield's EPSRC Impact Accrelate Account
源URL[http://ir.iggcas.ac.cn/handle/132A11/101954]  
专题中国科学院地质与地球物理研究所
通讯作者Zhao, Yifan
作者单位1.Jaguar Land Rover, Res & Technol, Warwick CV34 6TB, England
2.Chinese Acad Sci, Inst Geol & Geophys, Beijing 100029, Peoples R China
3.JP Morgan, London E14 5JP, England
4.Cranfield Univ, Sch Aerosp Transport & Mfg, Cranfield MK43 0AL, Beds, England
推荐引用方式
GB/T 7714		 Yang, Lichao,Yang, Ting-Yu,Liu, Haochen,et al. A Refined Non-Driving Activity Classification Using a Two-Stream Convolutional Neural Network[J]. IEEE SENSORS JOURNAL,2021,21(14):15574-15583.
APA Yang, Lichao.,Yang, Ting-Yu.,Liu, Haochen.,Shan, Xiaocai.,Brighton, James.,...&Zhao, Yifan.(2021).A Refined Non-Driving Activity Classification Using a Two-Stream Convolutional Neural Network.IEEE SENSORS JOURNAL,21(14),15574-15583.
MLA Yang, Lichao,et al."A Refined Non-Driving Activity Classification Using a Two-Stream Convolutional Neural Network".IEEE SENSORS JOURNAL 21.14(2021):15574-15583.

入库方式： OAI收割

来源：地质与地球物理研究所

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。