Image Segmentation-Based Bicycle Riding Side Identification Method

被引:3
作者
Kim, Jeyoen [1 ]
Soma, Takumi [2 ,3 ]
Manabe, Tetsuya [3 ]
Kojima, Aya [3 ]
机构
[1] Natl Inst Technol, Tsuruoka Coll, Dept Creat Engn, Tsuruoka 9978511, Japan
[2] Natl Inst Technol, Tsuruoka Coll, Adv Engn Course, Tsuruoka 9978511, Japan
[3] Saitama Univ, Grad Sch Sci & Engn, Saitama 3388570, Japan
关键词
bicycle riding side; image segmentation; advanced bicycle navigation system; bicycle riding safety support system;
D O I
10.1587/transfun.2022WBP0003
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This paper attempts to identify which side of the road a bicycle is currently riding on using a common camera for realizing an ad-vanced bicycle navigation system and bicycle riding safety support system. To identify the roadway area, the proposed method performs semantic seg-mentation 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.
引用
收藏
页码:775 / 783
页数:9
相关论文
共 31 条
  • [1] Ahmad M.B.B., 2020, PROC IEEE INT C CONT, DOI [10.1145/3377049.3377118, DOI 10.1145/3377049.3377118]
  • [2] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
    Chen, Liang-Chieh
    Zhu, Yukun
    Papandreou, George
    Schroff, Florian
    Adam, Hartwig
    [J]. COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 : 833 - 851
  • [3] Chen TR, 2015, IEEE INT VEH SYM, P617, DOI 10.1109/IVS.2015.7225753
  • [4] The Cityscapes Dataset for Semantic Urban Scene Understanding
    Cordts, Marius
    Omran, Mohamed
    Ramos, Sebastian
    Rehfeld, Timo
    Enzweiler, Markus
    Benenson, Rodrigo
    Franke, Uwe
    Roth, Stefan
    Schiele, Bernt
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3213 - 3223
  • [5] Using CyclePhilly data to assess wrong-way riding of cyclists in Philadelphia
    Dhakal, Nirbesh
    Cherry, Christopher R.
    Ling, Ziwen
    Azad, Mojdeh
    [J]. JOURNAL OF SAFETY RESEARCH, 2018, 67 : 145 - 153
  • [6] Foucher P, 2011, IEEE INT C INTELL TR, P1747, DOI 10.1109/ITSC.2011.6082840
  • [7] BikeMate: Bike Riding Behavior Monitoring with Smartphones
    Gu, Weixi
    Zhou, Zimu
    Zhou, Yuxun
    Zou, Han
    Liu, Yunxin
    Spanos, Costas J.
    Zhang, Lin
    [J]. PROCEEDINGS OF THE 14TH EAI INTERNATIONAL CONFERENCE ON MOBILE AND UBIQUITOUS SYSTEMS: COMPUTING, NETWORKING AND SERVICES (MOBIQUITOUS 2017), 2017, : 313 - 322
  • [8] Japan Bicycle Promotion Institute, 2017, BICYCLE STAT JAPAN 5
  • [9] Kasyanov A, 2017, IEEE INT C INT ROBOT, P6662, DOI 10.1109/IROS.2017.8206581
  • [10] Risky riding: Naturalistic methods comparing safety behavior from conventional bicycle riders and electric bike riders
    Langford, Brian Casey
    Chen, Jiaoli
    Cherry, Christopher R.
    [J]. ACCIDENT ANALYSIS AND PREVENTION, 2015, 82 : 220 - 226