Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Personal Mobility Safety Assistants using Object Detection based on Deep Learning

딥러닝 기반 객체 인식을 활용한 퍼스널 모빌리티 안전 보조 시스템 개발

  • Kwak, Hyeon-Seo (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Kim, Min-Young (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Jeon, Ji-Yong (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Jeong, Eun-Hye (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Kim, Ju-Yeop (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Hyeon, So-Dam (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Jeong, Jin-Woo (Department of Computer Engineering, Kumoh National Institute of Technology)
  • Received : 2021.01.25
  • Accepted : 2021.02.18
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the demand for the use of personal mobility vehicles, such as an electric kickboard, is increasing explosively because of its high portability and usability. However, the number of traffic accidents caused by personal mobility vehicles has also increased rapidly in recent years. To address the issues regarding the driver's safety, we propose a novel approach that can monitor context information around personal mobility vehicles using deep learning-based object detection and smartphone captured videos. In the proposed framework, a smartphone is attached to a personal mobility device and a front or rear view is recorded to detect an approaching object that may affect the driver's safety. Through the detection results using YOLOv5 model, we report the preliminary results and validated the feasibility of the proposed approach.

Keywords

References

  1. J. H. Choi, "Micro mobility: focusing on shared electric kickboards," KDB Future Strategy Research Institute, Korea, KDB Monthly 768, pp. 37-53, 2019.
  2. S. R. Kim, "Investigation of the usage of personal mobility," The Korea Transport Institute Brief, vol. 1, no. 3, pp. 4-7, Aug. 2017.
  3. ChosunBiz. Electric kickboard accident increased by 135% compared to a year ago. [Internet]. Available: https://biz.chosun.com/site/data/html_dir/2020/12/20/2020122000349.html.
  4. COCO Consortium. COCO: common objects in context [Internet]. Available: https://cocodataset.org/.
  5. Ultralytics. YOLOv5 [Internet]. Available: https://github.com/ultralytics/yolov5.
  6. C. Y. Wang, H. M. Liao, Y. H. Wu, P. Y. Chen, and J. W. Hsieh, "CSPNet: A New Backbone that can Enhance Learning Capability of CNN," in Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach: CA, pp. 390-391, 2020.
  7. T. H. Tran and J. W. Jeon, "Accurate Real-Time Traffic Light Detection Using YOLOv4," in Proceeding of the 2020 IEEE International Conference on Consumer Electronics - Asia, Seoul, pp. 1-4, 2020.