Journal of Industrial Convergence (산업융합연구)

DAEHAN Society of Industrial Management (대한산업경영학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Warning Devices for Personal Mobility Using Road Detection Image Processing and Sensors

노면 탐지 영상처리 및 센서를 활용한 개인형 이동장치용 경고 장치 설계

  • Su-Jin Choi (Dept. of Information & Communication Engineering, Sungkyul University) ;
  • Ga-Eun Kim (Dept. of Information & Communication Engineering, Sungkyul University) ;
  • Da-Un Shin (Dept. of Information & Communication Engineering, Sungkyul University) ;
  • Ji-Yeon Park (Dept. of Information & Communication Engineering, Sungkyul University) ;
  • Hyung-Jin Mun (Dept. of Information & Communication Engineering, Sungkyul University)
  • 최수진 (성결대학교 정보통신공학과) ;
  • 김가은 (성결대학교 정보통신공학과) ;
  • 신다운 (성결대학교 정보통신공학과) ;
  • 박지연 (성결대학교 정보통신공학과) ;
  • 문형진 (성결대학교 정보통신공학과)
  • Received : 2024.07.09
  • Accepted : 2024.10.20
  • Published : 2024.10.28
Download PDF
⟨ Previous Next ⟩

Abstract

Personal Mobility devices pose a significant safety risk to users depending on road conditions. With the recent surge in usage, the number of accidents has also increased, highlighting the need for a preventative system. This study aims to design and develop a warning system to enhance the safety of drivers by detecting road obstacles. To achieve this, a dataset is constructed using images of road obstacles, and the YOLOv5 model is trained. The system is based on the Raspberry Pi 4B, which processes video frames captured by a camera in real-time and triggers an LED warning when an obstacle is detected. The Flask framework is used to monitor the obstacle detection status in real time. Additionally, a GPS sensor is utilized to collect the user's location and speed data, and an auditory warning is triggered via a buzzer if the set speed is exceeded. In the future, this system could be expanded to transmit detected road obstacles and GPS information to a server, providing users with real-time road safety information. The results of this study can serve as essential technology for developing such a system.

개인형 이동장치(Personal Mobility)는 노면 상태에 따라 사용자의 안전에 큰 위협이 된다. 최근 사용이 급증하면서 사고 건수도 함께 증가하고 있어, 이를 예방하기 위한 시스템이 필요하다. 본 연구는 노면 장애물을 감지하여 운전자의 안전을 향상시키기 위한 경고 시스템을 설계하고 개발한다. 이를 위해 노면 장애물의 이미지를 기반으로 데이터셋을 구성하고 YOLOv5 모델을 학습시킨다. 이후 라즈베리파이 4B를 기반으로 하여 카메라로 촬영된 영상을 실시간 프레임 단위로 처리하고 노면 장애물이 감지되면 LED 경고를 발생시킨다. Flask 프레임워크를 활용하여 실시간으로 장애물 감지 상태를 모니터링 한다. 또한, GPS 센서를 활용하여 사용자의 위치 및 속도 정보를 수집하고, 설정 속도를 초과할 경우 버저를 통해 청각 경고를 발생시키는 시스템을 개발한다. 향후 사용자의 운행 과정에서 발견된 노면 장애물과 GPS 정보를 서버에 전송하여 실시간으로 노면 안전 상태를 제공하는 시스템으로 확장할 수 있으며, 본 연구 결과는 이러한 시스템 개발의 요소기술로 활용될 가능성이 높다.

Keywords

References

  1. D. Han (2020). Analysis of severity factors in personal mobility (PM) traffic accidents. Journal of Korean Society of Transportation, 38(3), 232-247. DOI: 10.7470/jkst.2020.38.3.232
  2. Korea Institute of Transport and Logistics. (2018). Development of Personal Mobility Safety System Using AI Image Object Recognition Technology. Journal of the Korea Institute Of Information and Communication Engineering, 25(3), 486-489. DOI: 10.6109/jkiice.2021.25.3.486
  3. Road Traffic Authority. (2023, April 6). Road Traffic Authority press release, personal mobility device (PM) traffic accidents increase every year. Retrieved from http://www.koroad.or.kr
  4. N. E Kang, M. H. Roh, H. J. Kim & S. R. Oh (2023). Development of Personal Mobility Safety System Using AI Image Object Recognition Technology. Journal of the Korea Institute Of Information and Communication Engineering, 25(3), 486-489. DOI: 10.6109/jkiice.2021.25.3.486
  5. K. O' Shea (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458.
  6. Y. H Lee & Y. S Kim (2020). CNN and YOLO performance comparison experiment for object detection. Journal of the Semiconductor & Display Technology, 19(1), 85-92.
  7. M. S. Joo (2018). A study on real-time object segmentation using deep learning and image processing techniques. Korea University. Retrieved from https://www.riss.kr/link?id=T14704785
  8. H. J. Mun and M. H. Lee.(2022). Design for Visitor Authentication Based on Face Recognition Technology Using CCTV. IEEE Access, 10, 124604-124618. DOI: 10.1109/ACCESS.2022.3223374
  9. M. Lee & H. Mun. (2020). Comparison analysis and case study for deep learning-based object detection algorithm. International Journal of Advanced Science and Convergence, 2(4), 7-16. DOI: 10.22662/IJASC.2020.2.4.007
  10. G. E. Kim, D. U. Sin, S. J. Choi & H. J. Mun (2024, January). Design of Warning Device for Personal Mobility using Road Detection Image Processing and Sensors. In Proceedings of the 2024 KLife Conference (pp. 15).
  11. A. Wang, H. Chen, L. Liu, K. Chen, Z. Lin, J. Han & G. Ding. (2024). Yolov10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458.