Image Segmentation-Based Bicycle Riding Side Identification Method

Jeyoen KIM; Takumi SOMA; Tetsuya MANABE; Aya KOJIMA

doi:10.1587/transfun.2022WBP0003

Image Segmentation-Based Bicycle Riding Side Identification Method

Jeyoen KIM, Takumi SOMA, Tetsuya MANABE, Aya KOJIMA

Full Text Views

26

Cite this

Summary :

This paper attempts to identify which side of the road a bicycle is currently riding on using a common camera for realizing an advanced bicycle navigation system and bicycle riding safety support system. To identify the roadway area, the proposed method performs semantic segmentation on a front camera image captured by a bicycle drive recorder or smartphone. If the roadway area extends from the center of the image to the right, the bicyclist is riding on the left side of the roadway (i.e., the correct riding position in Japan). In contrast, if the roadway area extends to the left, the bicyclist is on the right side of the roadway (i.e., the incorrect riding position in Japan). We evaluated the accuracy of the proposed method on various road widths with different traffic volumes using video captured by riding bicycles in Tsuruoka City, Yamagata Prefecture, and Saitama City, Saitama Prefecture, Japan. High accuracy (>80%) was achieved for any combination of the segmentation model, riding side identification method, and experimental conditions. Given these results, we believe that we have realized an effective image segmentation-based method to identify which side of the roadway a bicycle riding is on.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E106-A No.5 pp.775-783

Publication Date: 2023/05/01

Publicized: 2022/11/02

Online ISSN: 1745-1337

DOI: 10.1587/transfun.2022WBP0003

Type of Manuscript: Special Section PAPER (Special Section on Intelligent Transport Systems and Wideband Systems)

Category

Authors

Jeyoen KIM
  Tsuruoka College
Takumi SOMA
  Tsuruoka College,Saitama University
Tetsuya MANABE
  Saitama University
Aya KOJIMA
  Saitama University

Keyword

bicycle riding side, image segmentation, advanced bicycle navigation system, bicycle riding safety support system

Cite this

Copy

Jeyoen KIM, Takumi SOMA, Tetsuya MANABE, Aya KOJIMA, "Image Segmentation-Based Bicycle Riding Side Identification Method" in IEICE TRANSACTIONS on Fundamentals, vol. E106-A, no. 5, pp. 775-783, May 2023, doi: 10.1587/transfun.2022WBP0003.
Abstract: This paper attempts to identify which side of the road a bicycle is currently riding on using a common camera for realizing an advanced bicycle navigation system and bicycle riding safety support system. To identify the roadway area, the proposed method performs semantic segmentation on a front camera image captured by a bicycle drive recorder or smartphone. If the roadway area extends from the center of the image to the right, the bicyclist is riding on the left side of the roadway (i.e., the correct riding position in Japan). In contrast, if the roadway area extends to the left, the bicyclist is on the right side of the roadway (i.e., the incorrect riding position in Japan). We evaluated the accuracy of the proposed method on various road widths with different traffic volumes using video captured by riding bicycles in Tsuruoka City, Yamagata Prefecture, and Saitama City, Saitama Prefecture, Japan. High accuracy (>80%) was achieved for any combination of the segmentation model, riding side identification method, and experimental conditions. Given these results, we believe that we have realized an effective image segmentation-based method to identify which side of the roadway a bicycle riding is on.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2022WBP0003/_p

Copy

@ARTICLE{e106-a_5_775,
author={Jeyoen KIM, Takumi SOMA, Tetsuya MANABE, Aya KOJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Image Segmentation-Based Bicycle Riding Side Identification Method},
year={2023},
volume={E106-A},
number={5},
pages={775-783},
abstract={This paper attempts to identify which side of the road a bicycle is currently riding on using a common camera for realizing an advanced bicycle navigation system and bicycle riding safety support system. To identify the roadway area, the proposed method performs semantic segmentation on a front camera image captured by a bicycle drive recorder or smartphone. If the roadway area extends from the center of the image to the right, the bicyclist is riding on the left side of the roadway (i.e., the correct riding position in Japan). In contrast, if the roadway area extends to the left, the bicyclist is on the right side of the roadway (i.e., the incorrect riding position in Japan). We evaluated the accuracy of the proposed method on various road widths with different traffic volumes using video captured by riding bicycles in Tsuruoka City, Yamagata Prefecture, and Saitama City, Saitama Prefecture, Japan. High accuracy (>80%) was achieved for any combination of the segmentation model, riding side identification method, and experimental conditions. Given these results, we believe that we have realized an effective image segmentation-based method to identify which side of the roadway a bicycle riding is on.},
keywords={},
doi={10.1587/transfun.2022WBP0003},
ISSN={1745-1337},
month={May},}

Copy

TY - JOUR
TI - Image Segmentation-Based Bicycle Riding Side Identification Method
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 775
EP - 783
AU - Jeyoen KIM
AU - Takumi SOMA
AU - Tetsuya MANABE
AU - Aya KOJIMA
PY - 2023
DO - 10.1587/transfun.2022WBP0003
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E106-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2023
AB - This paper attempts to identify which side of the road a bicycle is currently riding on using a common camera for realizing an advanced bicycle navigation system and bicycle riding safety support system. To identify the roadway area, the proposed method performs semantic segmentation on a front camera image captured by a bicycle drive recorder or smartphone. If the roadway area extends from the center of the image to the right, the bicyclist is riding on the left side of the roadway (i.e., the correct riding position in Japan). In contrast, if the roadway area extends to the left, the bicyclist is on the right side of the roadway (i.e., the incorrect riding position in Japan). We evaluated the accuracy of the proposed method on various road widths with different traffic volumes using video captured by riding bicycles in Tsuruoka City, Yamagata Prefecture, and Saitama City, Saitama Prefecture, Japan. High accuracy (>80%) was achieved for any combination of the segmentation model, riding side identification method, and experimental conditions. Given these results, we believe that we have realized an effective image segmentation-based method to identify which side of the roadway a bicycle riding is on.
ER -