IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

IoT based Wearable Smart Safety Equipment using Image Processing

영상 처리를 이용한 IoT 기반 웨어러블 스마트 안전장비

  • Received : 2022.02.11
  • Accepted : 2022.04.20
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

With the recent expansion of electric kickboards and bicycle sharing services, more and more people use them. In addition, the rapid growth of the delivery business due to the COVID-19 has significantly increased the use of two-wheeled vehicles and personal mobility. As the accident rate increases, the rule related to the two-wheeled vehicles is changed to 'mandatory helmets for kickboards and single-person transportation' and was revised to prevent boarding itself without driver's license. In this paper, we propose a wearable smart safety equipment, called SafetyHelmet, that can keep helmet-wearing duty and lower the accident rate with the communication between helmets and mobile devices. To make this function available, we propose a safe driving assistance function by notifying the driver when an object that interferes with driving such as persons or other vehicles are detected by applying the YOLO v5 object detection algorithm. Therefore it is intended to provide a safer driving assistance by reducing the failure rate to identify dangers while driving single-person transportation.

Keywords

Acknowledgement

이 논문은 부경대학교 자율창의학술연구비 (2021년)에 의하여 연구되었음.

References

  1. The Hankyoreh, "Status of Personal Mobility Sharing Service", 2020; https://www.hani.co.kr/arti/specialsection/esc_section/959529.html (in Korean).
  2. Electronic Times, "Electric kickboard accidents in 2030 are half... Requires mandatory safety education when renting", 2020; https://m.etnews.com/20201004000099 (in Korean).
  3. H. Y. Kim, Internet of Things - Concept, Implementation Technology and Business, Hongneung Science Publishing House, 2014 (in Korean).
  4. S. W. Kum, T. B. Lim, J. I. Park. "Design and Implementation of IoT Collaboration Module Supporting User Context Management," IEMEK J. of Embed. Sys. Appl., Vol. 10, No. 3, pp. 129-137, 2015 (in Korean). https://doi.org/10.14372/IEMEK.2015.10.3.129
  5. Smart4u Smart Bike Helmet. https://www.amazon.com/smart4u-Comfortable-Lightweight-Breathable-Waterproof/dp/ B07RM1RL FL?th=1
  6. Tech Recipe, "Apple Watch Hand Signal Blinks Indicator... LED Bike Helmet", 2020; https://techrecipe.com/posts/18104
  7. Lumos: (2021.09.25.).: https://lumoshelmet.co/products/lumos-ultra
  8. S. Dasiopoulou, V. Mezaris, I. Kompatsiaris, V. K. Papastathis, M. G. Strintzis, "Knowledge-assisted Semantic Video Object Detection." IEEE Transactions on Circuits and Systems for Video Technology Vol. 15. No. 10, pp. 1210-1224, 2005. https://doi.org/10.1109/TCSVT.2005.854238
  9. J. Redmon, S. Divvala, R. Girshick. "You Only Look Once: Unified, Real-time Object Detection," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
  10. https://docs.ultralytics.com/#yolov5
  11. https://towardsdatascience.com/yolov5-compared-to-faster-rcnn-who-wins- a771cd6c9fb4
  12. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, "SSD: Single Shot Multibox Detector," in Proc. of European Conference on Computer Vision. pp. 21-37, 2016.
  13. https://cocodataset.org /#home
  14. H. Kim, H. J. Lee, "Development of Video Surveillance System Based on Image Processing and Machine Learning," 2017 Korean Society of Electronics Engineers Summer Conference, pp. 1547-1579, 2017 (in Korean).
  15. H. G. Choi et al., "Real-Time Object Recognition and Reporting System," Proc. of KIISE, pp. 2107-2109, 2017. (in Korean).