Road marking blur detection with drive recorder

Makoto Kawano, Kazuhiro Mikami, Satoshi Yokoyama, Takuro Yonezawa, Jin Nakazawa

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

5 Citations (Scopus)

Abstract

Can we inspect the road condition at a low cost? City infrastructures, such as roads are very important for citizens to their city lives. Roads require constant inspection and repair due to deterioration, but it is expensive to do so with manual labor. Meanwhile, there are official city vehicles, especially garbage trucks that run through the entire area of a city every day and have cameras to record their driving. When we use these cameras, we can watch roads conditions anytime, anywhere. In our study, we focus on these cameras and attempt detecting the road damage, such as road marking blur. To achieve our goal, we explore the new system in this paper. This system adopts the object detection approach that is end-to-end learning and based on deep neural networks, which propose the blur region candidate and detect whether the road markings are blurred or not all at once. In our experiment, first, we obtain the drive recorder video from sanitation engineer and then annotate them. After annotation, we trained our models and calculate the mean average precision to evaluate our models. As a result, our model performs on our collected dataset.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Big Data, Big Data 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4092-4097
Number of pages6
Volume2018-January
ISBN (Electronic)9781538627143
DOIs
Publication statusPublished - 2018 Jan 12
Event5th IEEE International Conference on Big Data, Big Data 2017 - Boston, United States
Duration: 2017 Dec 112017 Dec 14

Other

Other5th IEEE International Conference on Big Data, Big Data 2017
CountryUnited States
CityBoston
Period17/12/1117/12/14

Fingerprint

Camera
Cameras
Garbage trucks
Sanitation
Object Detection
Deterioration
Repair
Annotation
Inspection
Damage
Infrastructure
Entire
Model
Personnel
Neural Networks
Engineers
Calculate
Evaluate
Experiment
Roads

Keywords

  • Automotive sensing
  • Deep Learning
  • Object detection
  • Road inspection
  • Smart cities

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems
  • Information Systems and Management
  • Control and Optimization

Cite this

Kawano, M., Mikami, K., Yokoyama, S., Yonezawa, T., & Nakazawa, J. (2018). Road marking blur detection with drive recorder. In Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017 (Vol. 2018-January, pp. 4092-4097). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData.2017.8258427

Road marking blur detection with drive recorder. / Kawano, Makoto; Mikami, Kazuhiro; Yokoyama, Satoshi; Yonezawa, Takuro; Nakazawa, Jin.

Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 4092-4097.

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

Kawano, M, Mikami, K, Yokoyama, S, Yonezawa, T & Nakazawa, J 2018, Road marking blur detection with drive recorder. in Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 4092-4097, 5th IEEE International Conference on Big Data, Big Data 2017, Boston, United States, 17/12/11. https://doi.org/10.1109/BigData.2017.8258427
Kawano M, Mikami K, Yokoyama S, Yonezawa T, Nakazawa J. Road marking blur detection with drive recorder. In Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 4092-4097 https://doi.org/10.1109/BigData.2017.8258427
Kawano, Makoto ; Mikami, Kazuhiro ; Yokoyama, Satoshi ; Yonezawa, Takuro ; Nakazawa, Jin. / Road marking blur detection with drive recorder. Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 4092-4097
@inproceedings{d4346a5fbf1b46aca612ba3bcea21955,
title = "Road marking blur detection with drive recorder",
abstract = "Can we inspect the road condition at a low cost? City infrastructures, such as roads are very important for citizens to their city lives. Roads require constant inspection and repair due to deterioration, but it is expensive to do so with manual labor. Meanwhile, there are official city vehicles, especially garbage trucks that run through the entire area of a city every day and have cameras to record their driving. When we use these cameras, we can watch roads conditions anytime, anywhere. In our study, we focus on these cameras and attempt detecting the road damage, such as road marking blur. To achieve our goal, we explore the new system in this paper. This system adopts the object detection approach that is end-to-end learning and based on deep neural networks, which propose the blur region candidate and detect whether the road markings are blurred or not all at once. In our experiment, first, we obtain the drive recorder video from sanitation engineer and then annotate them. After annotation, we trained our models and calculate the mean average precision to evaluate our models. As a result, our model performs on our collected dataset.",
keywords = "Automotive sensing, Deep Learning, Object detection, Road inspection, Smart cities",
author = "Makoto Kawano and Kazuhiro Mikami and Satoshi Yokoyama and Takuro Yonezawa and Jin Nakazawa",
year = "2018",
month = "1",
day = "12",
doi = "10.1109/BigData.2017.8258427",
language = "English",
volume = "2018-January",
pages = "4092--4097",
booktitle = "Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Road marking blur detection with drive recorder

AU - Kawano, Makoto

AU - Mikami, Kazuhiro

AU - Yokoyama, Satoshi

AU - Yonezawa, Takuro

AU - Nakazawa, Jin

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Can we inspect the road condition at a low cost? City infrastructures, such as roads are very important for citizens to their city lives. Roads require constant inspection and repair due to deterioration, but it is expensive to do so with manual labor. Meanwhile, there are official city vehicles, especially garbage trucks that run through the entire area of a city every day and have cameras to record their driving. When we use these cameras, we can watch roads conditions anytime, anywhere. In our study, we focus on these cameras and attempt detecting the road damage, such as road marking blur. To achieve our goal, we explore the new system in this paper. This system adopts the object detection approach that is end-to-end learning and based on deep neural networks, which propose the blur region candidate and detect whether the road markings are blurred or not all at once. In our experiment, first, we obtain the drive recorder video from sanitation engineer and then annotate them. After annotation, we trained our models and calculate the mean average precision to evaluate our models. As a result, our model performs on our collected dataset.

AB - Can we inspect the road condition at a low cost? City infrastructures, such as roads are very important for citizens to their city lives. Roads require constant inspection and repair due to deterioration, but it is expensive to do so with manual labor. Meanwhile, there are official city vehicles, especially garbage trucks that run through the entire area of a city every day and have cameras to record their driving. When we use these cameras, we can watch roads conditions anytime, anywhere. In our study, we focus on these cameras and attempt detecting the road damage, such as road marking blur. To achieve our goal, we explore the new system in this paper. This system adopts the object detection approach that is end-to-end learning and based on deep neural networks, which propose the blur region candidate and detect whether the road markings are blurred or not all at once. In our experiment, first, we obtain the drive recorder video from sanitation engineer and then annotate them. After annotation, we trained our models and calculate the mean average precision to evaluate our models. As a result, our model performs on our collected dataset.

KW - Automotive sensing

KW - Deep Learning

KW - Object detection

KW - Road inspection

KW - Smart cities

UR - http://www.scopus.com/inward/record.url?scp=85047770688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047770688&partnerID=8YFLogxK

U2 - 10.1109/BigData.2017.8258427

DO - 10.1109/BigData.2017.8258427

M3 - Conference contribution

VL - 2018-January

SP - 4092

EP - 4097

BT - Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -