Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather

Kunming Li; Yu Li; Shaodi You; Nick Barnes

doi:10.1109/ICCVW.2017.65

Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather

Kunming Li, Yu Li, Shaodi You, Nick Barnes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

26 Citations (Scopus)

Abstract

Modern data-driven computer vision algorithms require a large volume, varied data for validation or evaluation. We utilize computer graphics techniques to generate a large volume foggy image dataset of road scenes with different levels of fog. We compare with other popular synthesized datasets, including data collected both from the virtual world and the real world. In addition, we benchmark recent popular dehazing methods and evaluate their performance on different datasets, which provides us an objectively comparison of their limitations and strengths. To our knowledge, this is the first foggy and hazy dataset with large volume data which can be helpful for computer vision research in the autonomous driving.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	491-500
Number of pages	10
ISBN (Electronic)	9781538610343
DOIs	https://doi.org/10.1109/ICCVW.2017.65
Publication status	Published - 1 Jul 2017
Event	16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy Duration: 22 Oct 2017 → 29 Oct 2017

Publication series

Name	Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Volume	2018-January

Conference

Conference	16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Country/Territory	Italy
City	Venice
Period	22/10/17 → 29/10/17

Access to Document

10.1109/ICCVW.2017.65

Cite this

Li, K., Li, Y., You, S., & Barnes, N. (2017). Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 (pp. 491-500). (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2017.65

Li, Kunming ; Li, Yu ; You, Shaodi et al. / Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 491-500 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017).

@inproceedings{a009c4cfc85e484a9922bce72c3451f5,

title = "Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather",

abstract = "Modern data-driven computer vision algorithms require a large volume, varied data for validation or evaluation. We utilize computer graphics techniques to generate a large volume foggy image dataset of road scenes with different levels of fog. We compare with other popular synthesized datasets, including data collected both from the virtual world and the real world. In addition, we benchmark recent popular dehazing methods and evaluate their performance on different datasets, which provides us an objectively comparison of their limitations and strengths. To our knowledge, this is the first foggy and hazy dataset with large volume data which can be helpful for computer vision research in the autonomous driving.",

author = "Kunming Li and Yu Li and Shaodi You and Nick Barnes",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 ; Conference date: 22-10-2017 Through 29-10-2017",

year = "2017",

month = jul,

day = "1",

doi = "10.1109/ICCVW.2017.65",

language = "English",

series = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "491--500",

booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",

address = "United States",

}

Li, K, Li, Y, You, S & Barnes, N 2017, Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather. in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 491-500, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCVW.2017.65

Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather. / Li, Kunming; Li, Yu; You, Shaodi et al.
Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 491-500 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather

AU - Li, Kunming

AU - Li, Yu

AU - You, Shaodi

AU - Barnes, Nick

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Modern data-driven computer vision algorithms require a large volume, varied data for validation or evaluation. We utilize computer graphics techniques to generate a large volume foggy image dataset of road scenes with different levels of fog. We compare with other popular synthesized datasets, including data collected both from the virtual world and the real world. In addition, we benchmark recent popular dehazing methods and evaluate their performance on different datasets, which provides us an objectively comparison of their limitations and strengths. To our knowledge, this is the first foggy and hazy dataset with large volume data which can be helpful for computer vision research in the autonomous driving.

AB - Modern data-driven computer vision algorithms require a large volume, varied data for validation or evaluation. We utilize computer graphics techniques to generate a large volume foggy image dataset of road scenes with different levels of fog. We compare with other popular synthesized datasets, including data collected both from the virtual world and the real world. In addition, we benchmark recent popular dehazing methods and evaluate their performance on different datasets, which provides us an objectively comparison of their limitations and strengths. To our knowledge, this is the first foggy and hazy dataset with large volume data which can be helpful for computer vision research in the autonomous driving.

UR - http://www.scopus.com/inward/record.url?scp=85046271707&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2017.65

DO - 10.1109/ICCVW.2017.65

M3 - Conference contribution

T3 - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

SP - 491

EP - 500

BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017

Y2 - 22 October 2017 through 29 October 2017

ER -

Li K, Li Y, You S, Barnes N. Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 491-500. (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017). doi: 10.1109/ICCVW.2017.65

Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this