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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
A Deep Learning-Based Framework for Intersectional Traffic Simulation and Editing

文献类型：期刊论文

作者Bi, Huikun2,3,4; Mao, Tianlu3; Wang, Zhaoqi3; Deng, Zhigang1
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2020-07-01
卷号26期号:7页码:2335-2348
关键词Trajectory Solid modeling Computational modeling Vehicle dynamics Traffic control Data models Deep learning Traffic simulation crowd simulation data-driven deep learning intersectional traffic
ISSN号1077-2626
DOI10.1109/TVCG.2018.2889834
英文摘要Most of existing traffic simulation methods have been focused on simulating vehicles on freeways or city-scale urban networks. However, relatively little research has been done to simulate intersectional traffic to date despite its broad potential applications. In this paper, we propose a novel deep learning-based framework to simulate and edit intersectional traffic. Specifically, based on an in-house collected intersectional traffic dataset, we employ the combination of convolution network (CNN) and recurrent network (RNN) to learn the patterns of vehicle trajectories in intersectional traffic. Besides simulating novel intersectional traffic, our method can be used to edit existing intersectional traffic. Through many experiments as well as comparative user studies, we demonstrate that the results by our method are visually indistinguishable from ground truth, and our method can outperform existing methods.
资助项目National Key Research and Development Program of China[2017YFC0804900] ; National Natural Science Foundation of China[61532002] ; 13th Five-Year Common Technology pre Research Program[41402050301-170441402065] ; Science and Technology Mobilization Program of Dongguan[KZ2017-06] ; US NSF[IIS 1524782] ; CSC Fellowship
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000542933100001
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/15132]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Deng, Zhigang
作者单位1.Univ Houston, Comp Sci Dept, Houston, TX 77004 USA
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China
4.Univ Houston, Comp Graph & Interact Media Lab, Houston, TX 77204 USA
推荐引用方式
GB/T 7714		 Bi, Huikun,Mao, Tianlu,Wang, Zhaoqi,et al. A Deep Learning-Based Framework for Intersectional Traffic Simulation and Editing[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2020,26(7):2335-2348.
APA Bi, Huikun,Mao, Tianlu,Wang, Zhaoqi,&Deng, Zhigang.(2020).A Deep Learning-Based Framework for Intersectional Traffic Simulation and Editing.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,26(7),2335-2348.
MLA Bi, Huikun,et al."A Deep Learning-Based Framework for Intersectional Traffic Simulation and Editing".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 26.7(2020):2335-2348.

入库方式： OAI收割

来源：计算技术研究所

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。