Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis

Hanwei Zhang; Hiroshi Kawasaki; Tsunenori Mine; Shintaro Ono

doi:10.1007/978-3-030-81638-4_6

Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis

Hanwei Zhang, Hiroshi Kawasaki, Tsunenori Mine, Shintaro Ono

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

Abstract

We study an often ignored problem, the discrimination between road conditions and weather in driving videos, which may possibly lead to imperceptible errors on driving data analysis. We explore BDD100K, a common driving video database, and Kyushu Driving Data, a huge driving database created by ourselves. In our experiments, we use road condition labels and weather labels respectively to train several deep models on driving image sequences and demonstrate the difference between the two varieties of labels. The results indicate a significant difference between the two varieties, which leads to different performance of deep models.

Original language	English
Title of host publication	Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers
Editors	Hieyong Jeong, Kazuhiko Sumi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	70-80
Number of pages	11
ISBN (Print)	9783030816377
DOIs	https://doi.org/10.1007/978-3-030-81638-4_6
Publication status	Published - 2021
Event	27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021 - Virtual, Online Duration: Feb 22 2021 → Feb 23 2021

Publication series

Name	Communications in Computer and Information Science
Volume	1405
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021
City	Virtual, Online
Period	2/22/21 → 2/23/21

All Science Journal Classification (ASJC) codes

Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-3-030-81638-4_6

Cite this

Zhang, H., Kawasaki, H., Mine, T., & Ono, S. (2021). Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis. In H. Jeong, & K. Sumi (Eds.), Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers (pp. 70-80). (Communications in Computer and Information Science; Vol. 1405). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-81638-4_6

Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis. / Zhang, Hanwei; Kawasaki, Hiroshi ; Mine, Tsunenori et al.

Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers. ed. / Hieyong Jeong; Kazuhiko Sumi. Springer Science and Business Media Deutschland GmbH, 2021. p. 70-80 (Communications in Computer and Information Science; Vol. 1405).

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

Zhang, H, Kawasaki, H , Mine, T & Ono, S 2021, Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis. in H Jeong & K Sumi (eds), Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers. Communications in Computer and Information Science, vol. 1405, Springer Science and Business Media Deutschland GmbH, pp. 70-80, 27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021, Virtual, Online, 2/22/21. https://doi.org/10.1007/978-3-030-81638-4_6

Zhang H, Kawasaki H , Mine T, Ono S. Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis. In Jeong H, Sumi K, editors, Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2021. p. 70-80. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-81638-4_6

Zhang, Hanwei ; Kawasaki, Hiroshi ; Mine, Tsunenori et al. / Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis. Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers. editor / Hieyong Jeong ; Kazuhiko Sumi. Springer Science and Business Media Deutschland GmbH, 2021. pp. 70-80 (Communications in Computer and Information Science).

@inproceedings{fbebbf49e23042008f1564846bab1c21,

title = "Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis",

abstract = "We study an often ignored problem, the discrimination between road conditions and weather in driving videos, which may possibly lead to imperceptible errors on driving data analysis. We explore BDD100K, a common driving video database, and Kyushu Driving Data, a huge driving database created by ourselves. In our experiments, we use road condition labels and weather labels respectively to train several deep models on driving image sequences and demonstrate the difference between the two varieties of labels. The results indicate a significant difference between the two varieties, which leads to different performance of deep models.",

author = "Hanwei Zhang and Hiroshi Kawasaki and Tsunenori Mine and Shintaro Ono",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021 ; Conference date: 22-02-2021 Through 23-02-2021",

year = "2021",

doi = "10.1007/978-3-030-81638-4_6",

language = "English",

isbn = "9783030816377",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "70--80",

editor = "Hieyong Jeong and Kazuhiko Sumi",

booktitle = "Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers",

address = "Germany",

}

TY - GEN

T1 - Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis

AU - Zhang, Hanwei

AU - Kawasaki, Hiroshi

AU - Mine, Tsunenori

AU - Ono, Shintaro

PY - 2021

Y1 - 2021

N2 - We study an often ignored problem, the discrimination between road conditions and weather in driving videos, which may possibly lead to imperceptible errors on driving data analysis. We explore BDD100K, a common driving video database, and Kyushu Driving Data, a huge driving database created by ourselves. In our experiments, we use road condition labels and weather labels respectively to train several deep models on driving image sequences and demonstrate the difference between the two varieties of labels. The results indicate a significant difference between the two varieties, which leads to different performance of deep models.

AB - We study an often ignored problem, the discrimination between road conditions and weather in driving videos, which may possibly lead to imperceptible errors on driving data analysis. We explore BDD100K, a common driving video database, and Kyushu Driving Data, a huge driving database created by ourselves. In our experiments, we use road condition labels and weather labels respectively to train several deep models on driving image sequences and demonstrate the difference between the two varieties of labels. The results indicate a significant difference between the two varieties, which leads to different performance of deep models.

UR - http://www.scopus.com/inward/record.url?scp=85112691873&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85112691873&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-81638-4_6

DO - 10.1007/978-3-030-81638-4_6

M3 - Conference contribution

AN - SCOPUS:85112691873

SN - 9783030816377

T3 - Communications in Computer and Information Science

SP - 70

EP - 80

BT - Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers

A2 - Jeong, Hieyong

A2 - Sumi, Kazuhiko

PB - Springer Science and Business Media Deutschland GmbH

T2 - 27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021

Y2 - 22 February 2021 through 23 February 2021

ER -

Focusing on Discrimination Between Road Conditions and Weather in Driving Video Analysis

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this