Road Weather Condition Estimation Using Fixed and Mobile Based Cameras

Koray Ozcan, Anuj Sharma, Skylar Knickerbocker, Jennifer I Merickel, Neal Hawkins, Matthew Rizzo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22% of all vehicle crashes and 16% of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57% and 77.32% road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways.

Original languageEnglish (US)
Title of host publicationAdvances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC
EditorsSupriya Kapoor, Kohei Arai
PublisherSpringer Verlag
Pages192-204
Number of pages13
ISBN (Print)9783030177942
DOIs
StatePublished - Jan 1 2020
EventComputer Vision Conference, CVC 2019 - Las Vegas, United States
Duration: Apr 25 2019Apr 26 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume943
ISSN (Print)2194-5357

Conference

ConferenceComputer Vision Conference, CVC 2019
CountryUnited States
CityLas Vegas
Period4/25/194/26/19

Fingerprint

Cameras
Snow plows
Snow
Television
Networks (circuits)
Cams
Image processing
Lighting

Keywords

  • CCTV
  • Mobile camera
  • Neural networks
  • Road weather classification
  • Scene classification
  • VGG16

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Ozcan, K., Sharma, A., Knickerbocker, S., Merickel, J. I., Hawkins, N., & Rizzo, M. (2020). Road Weather Condition Estimation Using Fixed and Mobile Based Cameras. In S. Kapoor, & K. Arai (Eds.), Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC (pp. 192-204). (Advances in Intelligent Systems and Computing; Vol. 943). Springer Verlag. https://doi.org/10.1007/978-3-030-17795-9_14

Road Weather Condition Estimation Using Fixed and Mobile Based Cameras. / Ozcan, Koray; Sharma, Anuj; Knickerbocker, Skylar; Merickel, Jennifer I; Hawkins, Neal; Rizzo, Matthew.

Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. ed. / Supriya Kapoor; Kohei Arai. Springer Verlag, 2020. p. 192-204 (Advances in Intelligent Systems and Computing; Vol. 943).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ozcan, K, Sharma, A, Knickerbocker, S, Merickel, JI, Hawkins, N & Rizzo, M 2020, Road Weather Condition Estimation Using Fixed and Mobile Based Cameras. in S Kapoor & K Arai (eds), Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. Advances in Intelligent Systems and Computing, vol. 943, Springer Verlag, pp. 192-204, Computer Vision Conference, CVC 2019, Las Vegas, United States, 4/25/19. https://doi.org/10.1007/978-3-030-17795-9_14
Ozcan K, Sharma A, Knickerbocker S, Merickel JI, Hawkins N, Rizzo M. Road Weather Condition Estimation Using Fixed and Mobile Based Cameras. In Kapoor S, Arai K, editors, Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. Springer Verlag. 2020. p. 192-204. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-17795-9_14
Ozcan, Koray ; Sharma, Anuj ; Knickerbocker, Skylar ; Merickel, Jennifer I ; Hawkins, Neal ; Rizzo, Matthew. / Road Weather Condition Estimation Using Fixed and Mobile Based Cameras. Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. editor / Supriya Kapoor ; Kohei Arai. Springer Verlag, 2020. pp. 192-204 (Advances in Intelligent Systems and Computing).
@inproceedings{471dd5a46c3e4ffa83937f87e8cd95be,
title = "Road Weather Condition Estimation Using Fixed and Mobile Based Cameras",
abstract = "Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22{\%} of all vehicle crashes and 16{\%} of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57{\%} and 77.32{\%} road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways.",
keywords = "CCTV, Mobile camera, Neural networks, Road weather classification, Scene classification, VGG16",
author = "Koray Ozcan and Anuj Sharma and Skylar Knickerbocker and Merickel, {Jennifer I} and Neal Hawkins and Matthew Rizzo",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-17795-9_14",
language = "English (US)",
isbn = "9783030177942",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "192--204",
editor = "Supriya Kapoor and Kohei Arai",
booktitle = "Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC",

}

TY - GEN

T1 - Road Weather Condition Estimation Using Fixed and Mobile Based Cameras

AU - Ozcan, Koray

AU - Sharma, Anuj

AU - Knickerbocker, Skylar

AU - Merickel, Jennifer I

AU - Hawkins, Neal

AU - Rizzo, Matthew

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22% of all vehicle crashes and 16% of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57% and 77.32% road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways.

AB - Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22% of all vehicle crashes and 16% of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57% and 77.32% road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways.

KW - CCTV

KW - Mobile camera

KW - Neural networks

KW - Road weather classification

KW - Scene classification

KW - VGG16

UR - http://www.scopus.com/inward/record.url?scp=85065465202&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065465202&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-17795-9_14

DO - 10.1007/978-3-030-17795-9_14

M3 - Conference contribution

SN - 9783030177942

T3 - Advances in Intelligent Systems and Computing

SP - 192

EP - 204

BT - Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC

A2 - Kapoor, Supriya

A2 - Arai, Kohei

PB - Springer Verlag

ER -