자율주행을 위한 YOLOv5 기반 신호등의 신호 분류 모델 연구

A Research of a Traffic Light Signal Classification Model using YOLOv5 for Autonomous Driving

  • 국중진 (상명대학교 정보보안공학과) ;
  • 이학승 (상명대학교 정보보안공학과)
  • Joongjin Kook (Dept. of Information Security Engineering, Sangmyung University) ;
  • Hakseung Lee (Dept. of Information Security Engineering, Sangmyung University)
  • 투고 : 2024.02.09
  • 심사 : 2024.03.20
  • 발행 : 2024.03.31

초록

As research on autonomous driving technology becomes more active, various studies on signal recognition of traffic lights are also being conducted. When recognizing traffic lights with different purposes and shapes, such as pedestrian traffic lights, vehicle-only traffic lights, and right-turn traffic lights, existing classification methods may cause misrecognition problems. Therefore, in this study, we studied a model that allows accurate signal recognition by subdividing the classification of signals according to the purpose and type of traffic lights. A signal recognition model was created by classifying traffic lights according to their shape and purpose into horizontal, vertical, right turn, etc., and by comparing them with the existing signal recognition model based on YOLOv5, it was confirmed that more correct and accurate recognition was possible.

키워드

과제정보

This research was funded by a 2023 research Grant from Sangmyung University.

참고문헌

  1. Kyung Bok Sung, Kyung Wook Min and Jung Dan Choi, "Trends and Key Technologies in Autonomous Vehicles: What Technologies are Utilized in Autonomous Vehicles?," J. of The Korean Institue of Communication Sciences, Vol. 35, No. 1, pp. 3-13, 2018.
  2. Hyeong Seok Kim, Young Joo Han and Joon Sang Park, "Impacts of Special Traffic Lights on Deep Learning Based Traffic Light Recognition Systems," The Journal of the KICS, Vol. 46, No. 3, pp. 526-531, 2021. https://doi.org/10.7840/kics.2021.46.3.526
  3. J. W. Yang, J. T. Kim and J. Y. Kim, "Study on Driver's Perception Reacation Times Against Different Types of Traffic Signals: Non-declarative and Declarative Memories Affected by Colors and Combinations of Signal lights," Journal of Korean Society of Transportation, pp. 240-250, 2018.
  4. Jang Won Kim, "Detection and Recognition of Traffic Lights for Unmanned Autonomous Driving," Journal of Korea Institute of Information, Electronics, and Communication Technology, Vol. 11, No. 6, pp. 751-756, 2018.
  5. Eun Oh Joo and Min Soo Kim, "Development of efficient traffic light information recognition method based on Yolov5 model," Jounal of Korean Society for Geospatial Information Science, Vol. 2021, No. 11, pp. 116-119, 2021.
  6. Ji-Eun Hawng, Dasol Ahn, Seunghwa Lee, Sung-Ho Park and Chun-Su Park, "Traffic Lights Detection and Recognition System Using Black-Box Images", Journal of the Semiconductor & Display Technology, Vol. 15, No. 2. 2016.
  7. J. U. Kim, C. Y. Jung, W. Hwang, D. J. Lim and H. J. Noh, "YOLO based Object detection for Autonomous driving and Collision," Journal of the HCI Society of Korea, Vol. 2023, No. 2, pp. 1107-1110, 2023.
  8. Y. S. Ha, H. S. Hwang, M. J. Kim, C. J. Lee and J. C. Shim, "A Prior Study on the Improvement of the Recognition Rate of Medieval Korean Using Class Compression and Division in Object Detection," Journal of Koear Multimedia Society, Vol. 26, No. 6, pp. 795-803, 2023. https://doi.org/10.9717/kmms.2023.26.6.795
  9. Gwang Su Lee, "Don't confuse the right turn signal with the auxiliary vehicle light ," Goyang Newspaper, 2023.05.31, https://www.mygoyang.com/news/articleView.html?idxno=73381, 2023.09.23.