Journal of Digital Policy (디지털정책학회지)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Object Detection and Warning Model for the Prevention of Right Turn Car Accidents

우회전 차량 사고 예방을 위한 객체 탐지 및 경고 모델 연구

  • Sang-Joon Cho (Department of Nano Semi-Conductor Engineering, Tech University of Korea) ;
  • Seong-uk Shin (Department of IT Convergence Semi-Conductor Engineering, Tech University of Korea) ;
  • Myeong-Jae Noh (Metatics)
  • 조상준 (한국공학대학교 나노반도체 공학과) ;
  • 신성욱 (한국공학대학교 IT반도체융합공학과) ;
  • 노명재 (메타틱스)
  • Received : 2023.10.27
  • Accepted : 2023.12.28
  • Published : 2023.12.28
Download PDF
⟨ Previous Next ⟩

Abstract

With a continuous occurrence of right-turn traffic accidents at intersections, there is an increasing demand for measures to address these incidents. In response, a technology has been developed to detect the presence of pedestrians through object detection in CCTV footage at right-turn areas and display warning messages on the screen to alert drivers. The YOLO (You Only Look Once) model, a type of object detection model, was employed to assess the performance of object detection. An algorithm was also devised to address misidentification issues and generate warning messages when pedestrians are detected. The accuracy of recognizing pedestrians or objects and outputting warning messages was measured at approximately 82%, suggesting a potential contribution to preventing right-turn accidents

교차로에서의 우회전 교통사고가 지속적으로 발생하면서 우회전 교통사고에 대한 대책 마련이 촉구되고 있다. 이에 우회전 지역의 CCTV 영상에서의 객체 탐지를 통해 보행자의 유무를 탐지하고 이를 디스플레이에 경고 문구를 출력해 운전자에게 알리는 기술을 개발하였다. 객체 탐지 모델 중 하나인 YOLO(You Only Look Once) 모델을 이용하여 객체 탐지의 성능평가를 확인하고, 추가적인 후처리 알고리즘을 통해 오인식 문제 해결 및 보행자 확인 시 경고 문구를 출력하는 알고리즘을 개발 하였다. 보행자 혹은 객체를 인식하여 경고 문구를 출력하는 정확도는 82% 수준으로 측정되었으며 이를 통해 우회전 사고 예방에 기여할 수 있을 것으로 예상된다.

Keywords

Acknowledgement

This work was supported by the Korea Environmental Industry & Technology Institute(KEITI) funded by the Ministry of Environment(MOE) (Training DX-based carbon supply network environmental experts). This work was supported by the Korea Institute of Energy Technology Evaluation and Planning(KETEP) and the Ministry of Trade, Industry & Energy(MOTIE) of the Republic of Korea (No. 20224000000200).

References

  1. Anonymous. (2023). KoROAD NEWS. Traffic Light. http://news.koroad.or.kr/koroad/vol73/sub/sub17.php 
  2. Ministry of Government Legislation. (2023). Enforcement Rules of the Road Traffic Act. https://www.law.go.kr/%EB%B2%95%EB%A0%B9/%EB%8F%84%EB%A1%9C%EA%B5%90%ED%86%B5%EB%B2%95%EC%8B%9C%ED%96%89%EA%B7%9C%EC%B9%99 
  3. H. M. Seo. (2023). The Hankyorh. Name of Site or Board. https://www.hani.co.kr/arti/society/society_general/1080126.html 
  4. C. M. Lee, W. S. Jeon, & S. Y. Rhee (2023). A Real-time System for Judging Vehicle Loads and Overloaded using Yolo with Post-Processing Algorithm. Journal of Korean Institute of Intelligent Systems, 33(5), 414-422, DOI : 10.5391/JKIIS.2023.33.5.414 
  5. S. H. Han, S. Chae, J. H. Park, Syed Ali Hassan, Tariq Rahim, & S. Y. Shin (2020). Video-Based Traffic Accident Prevention Safety System Using Deep Learning. The Journal of Korean Institute of Communications and Information Sciences, 45(8), 1399-1406, DOI : 10.7840/kics.2020.45.8.1399 
  6. Md Foysal Haque, H. Y. Lim, & D. S. Kang (2019). Real Time Object Detection Based on YOLO with Feature Filter Bank. The Journal of Korean Institute of Information Technology, 17(5), 91-97, DOI : 10.14801/jkiit.2019.17.5.91 
  7. Yuanyuan Tan, & Ge Yi (2023). Application of Convolutional Neural Network Classification Algorithm in Online-offline Blended Teaching of Chinese Painting. IEIE Transactions on Smart Processing & Computing, 12(3), DOI : 243-251,IESPC.2023.12.3.243  https://doi.org/10.5573/IEIESPC.2023.12.3.243
  8. J. S. Kim, T. H. Lee & J. H. Yeom (2023). Personal Mobility Detection through Application of YOLO Deep Learning Algorithm to Drone Images. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 41(4), 239-246 DOI : 10.7848/ksgpc.2023.41.4.239 
  9. H. J. Lee, & H. C. Jung (2022). Recyclable Objects Detection via Bounding Box CutMix and Standardized Distance-based IoU. Institute of Embedded Engineering of Korea, 17(5), 289-296, DOI : 10.14372/IEMEK.2022.17.5.289 
  10. M. G. Jung, S. H. An, & S. C. Park (2023). Learning Performance of Reinforcement Learning According to the Tensor Dimensions Representing States. Korean Journal of Computational Design and Engineering, 28(1), 1-9, DOI : 10.7315/CDE.2023.001 
  11. Y. C. Shin, E. J. Lee, S. J. Jang, Y. B. Kim, & J. H. Kwon (2022). Repulsion Distance Intersection over Union Loss for Crowd Scene Detection. TECHART: Journal of Arts and Imaging Science, 9(1), 27-30, DOI : 10.15323/techart.2022.2.9.1.27 
  12. S. H. Kang, Y. S. Shin, S. H. Lee, J. H. Park & J. M. Kang. (2022). Exponential NMS : A New NMS Method for Suppression of Overlapped Bounding Box in Detection of Steel Surface Defects. Journal of Korean Institute of Intelligent Systems, 32(6), 464-472. DOI : 10.5391/JKIIS.2022.32.6.464 
  13. M. S. Lee, D. M. Barker, & Y. H. Kuo (2006). Background Error Statistics using WRF Ensembles Generated by Randomized Control Variables. Asia-Pacific Journal of Atmospheric Sciences, 42(3), 153-167. 
  14. S. J. Kim, W. H. Son, J. H. Lee, H. H. Nguyen, & H. Y. Jeong (2023). Sampling-based Analysis of Labeling Errors in AI-Hub Traffic-Light Datasets. Journal of the Institute of Electronics and Information Engineers, 60(3), 109-112, DOI : 10.5573/ieie.2023.60.3.109 
  15. G. H. Park, et al. (2022). A Comparative Study on the Object Detection of Deposited Marine Debris (DMD) Using YOLOv5 and YOLOv7 Models. The Korean Society Of Remote sensing, 38(6), 1643-1652. 
  16. J. W. Han, S. H. Park, C. H. Sim, & J. W. Whang (2022). Development of Smart driving monitoring device for Personal Mobility through Confusion Matrix verification. Journal of the Korea Society of Computer and Information , 27(2), 61-69. https://doi.org/10.9708/JKSCI.2022.27.02.061