First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework
Existing programmable simulators enable researchers to customize different driving scenarios to conduct in-lab automotive driver simulations. However, software-based simulators for cognitive research generate and maintain their scenes with the support of 3D engines, which may affect users' expe...
| Main Authors: | , , , , |
|---|---|
| Format: | Book Section |
| Language: | English |
| Published: |
Association for Computing Machinery
2019
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/60666/ |
| _version_ | 1848799792124133376 |
|---|---|
| author | Song, Zili Wang, Shuolei Kong, Weikai Peng, Xiangjun Sun, Xu |
| author_facet | Song, Zili Wang, Shuolei Kong, Weikai Peng, Xiangjun Sun, Xu |
| author_sort | Song, Zili |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Existing programmable simulators enable researchers to customize different driving scenarios to conduct in-lab automotive driver simulations. However, software-based simulators for cognitive research generate and maintain their scenes with the support of 3D engines, which may affect users' experiences to a certain degree since they are not sufficiently realistic. Now, a critical issue is the question of how to build scenes into real-world ones. In this paper, we introduce the first step in utilizing video-to-video synthesis, which is a deep learning approach, in OpenDS framework, which is an open-source driving simulator software, to present simulated scenes as realistically as possible. Off-line evaluations demonstrated promising results from our study, and our future work will focus on how to merge them appropriately to build a close-to-reality, real-time driving simulator. |
| first_indexed | 2025-11-14T20:41:17Z |
| format | Book Section |
| id | nottingham-60666 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:41:17Z |
| publishDate | 2019 |
| publisher | Association for Computing Machinery |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-606662020-05-21T06:47:07Z https://eprints.nottingham.ac.uk/60666/ First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework Song, Zili Wang, Shuolei Kong, Weikai Peng, Xiangjun Sun, Xu Existing programmable simulators enable researchers to customize different driving scenarios to conduct in-lab automotive driver simulations. However, software-based simulators for cognitive research generate and maintain their scenes with the support of 3D engines, which may affect users' experiences to a certain degree since they are not sufficiently realistic. Now, a critical issue is the question of how to build scenes into real-world ones. In this paper, we introduce the first step in utilizing video-to-video synthesis, which is a deep learning approach, in OpenDS framework, which is an open-source driving simulator software, to present simulated scenes as realistically as possible. Off-line evaluations demonstrated promising results from our study, and our future work will focus on how to merge them appropriately to build a close-to-reality, real-time driving simulator. Association for Computing Machinery 2019-09-21 Book Section PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/60666/1/First%20Attempt%20to%20Build%20Realistic%20Driving%20Scenes%20using%20Video-to-video%20Synthesis%20in%20OpenDS%20Framework.pdf Song, Zili, Wang, Shuolei, Kong, Weikai, Peng, Xiangjun and Sun, Xu (2019) First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework. In: Proceedings of the 11th International Conference on Automotive User Interfaces and Interactive Vehicular Applications: Adjunct Proceedings. Association for Computing Machinery, Utrecht, Netherlands, pp. 387-391. ISBN 9781450369206 Video Synthesis; Driving Simulator; Machine Learning http://dx.doi.org/10.1145/3349263.3351497 doi:10.1145/3349263.3351497 doi:10.1145/3349263.3351497 |
| spellingShingle | Video Synthesis; Driving Simulator; Machine Learning Song, Zili Wang, Shuolei Kong, Weikai Peng, Xiangjun Sun, Xu First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title | First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title_full | First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title_fullStr | First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title_full_unstemmed | First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title_short | First attempt to build realistic driving scenes using video-to-video synthesis in OpenDS framework |
| title_sort | first attempt to build realistic driving scenes using video-to-video synthesis in opends framework |
| topic | Video Synthesis; Driving Simulator; Machine Learning |
| url | https://eprints.nottingham.ac.uk/60666/ https://eprints.nottingham.ac.uk/60666/ https://eprints.nottingham.ac.uk/60666/ |