International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Detecting Jaywalking Using the YOLOv5 Model

  • Kim, Hyun-Tae (Department of Computer Engineering, Honam University) ;
  • Lee, Sang-Hyun (Department of Computer Engineering, Honam University)
  • Received : 2022.05.28
  • Accepted : 2022.06.09
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, Korea is building traffic infrastructure using Intelligent Transport Systems (ITS), but the pedestrian traffic accident rate is very high. The purpose of this paper is to prevent the risk of traffic accidents by jaywalking pedestrians. The development of this study aims to detect pedestrians who trespass using the public data set provided by the Artificial Intelligence Hub (AIHub). The data set uses training data: 673,150 pieces and validation data: 131,385 pieces, and the types include snow, rain, fog, etc., and there is a total of 7 types including passenger cars, small buses, large buses, trucks, large trailers, motorcycles, and pedestrians. has a class format of Learning is carried out using YOLOv5 as an implementation model, and as an object detection and edge detection method of an input image, a canny edge model is applied to classify and visualize human objects within the detected road boundary range. In this study, it was designed and implemented to detect pedestrians using the deep learning-based YOLOv5 model. As the final result, the mAP 0.5 showed a real-time detection rate of 61% and 114.9 fps at 338 epochs using the YOLOv5 model.

Keywords

References

  1. http://taas.koroad.or.kr/
  2. M. -K. Ba and S. -H. Park, "A Study on the Street Environmental Characteristics Influencing Jaywalking Traffic Accidents," Journal of The Korean Regional Development Association, Vol. 30, No. 2, pp. 177-191, June 2018. https://doi.org/10.22885/KRDA.2018.30.2.177
  3. J. -H. Kim and Y. -H. Shin, "A Study on Deep Learning-based Pedestrian Detection and Alarm System," The Journal of The Korea Institute of Intelligent Transport Systems, Vol. 18, No. 4, pp. 58-70, Aug 2019. DOI: https://doi.org/10.12815/kits.2019.18.4.58
  4. Joseph Redmon and Ali Farhadi, "YOLO9000: better, faster, stronger," in Proc. of the IEEE conference on computer vision and pattern recognition, pp. 7263-7271, July, 2017. DOI: https://doi.org/10.48550/arXiv.1612.08242
  5. Redmon, Joseph and Ali Farhadi, "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.027 67, Apr 2018. DOI: https://doi.org/10.48550/arXiv.1804.02767
  6. Alexey Bochkovskiy, Chien-Yao Wang and Hong-Yuan Mark Liao, "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, Apr 23, 2020. DOI: https://doi.org/10.48550/arXiv.2004.10934
  7. H. T. Kim and S. H. Lee, "A study on object distance measurement using OpenCV-based YOLOv5," International Journal of Advanced Culture Technology, Vol. 9, No. 3, pp.298-304, 2021. DOI : https://doi.org/10.17703/IJACT.2021.9.3.298
  8. https://en.wikipedia.org/wiki/Canny_edge_detector
  9. https://AIHub.or.kr/aidata/34120
  10. J. -H. Yu, Y. -J. Han and H. -S. Hahn, "On-road Vehicle and Area Detection Using Edge Connectivity and Corner Clustering," The Institute of Electronics and Information Engineers, pp. 1035-1036, June 2008.
  11. J. -D. Oh, A study on the lane detection techniques for intelligent vehicle, MS Thesis. Sangji University, Gangwon-do, South Korea, 2016.