드라이브 ㆍ 컨트롤 (Journal of Drive and Control)

  • 제20권4호
  • /
  • Pages.92-99
  • /
  • 2023
  • /
  • 2671-7972(pISSN)
  • /
  • 2671-7980(eISSN)
유공압건설기계학회 (The Korean Society for Fluid Power and Construction Equipment)
권호 표지
DOI QR코드

DOI QR Code

가상환경 및 카메라 이미지를 활용한 실시간 속도 표지판 인식 방법

Real-time Speed Sign Recognition Method Using Virtual Environments and Camera Images

  • 송은지 ;
  • 김태윤 ;
  • 김효빈 ;
  • 김경호 ;
  • 황성호
  • Eunji Song (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Taeyun Kim (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Hyobin Kim (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Kyung-Ho Kim (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Sung-Ho Hwang (Department of Mechanical Engineering, Sungkyunkwan University)
  • 투고 : 2023.11.16
  • 심사 : 2023.11.23
  • 발행 : 2023.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.

키워드

과제정보

본 과제(결과물)는 교육부와 한국연구재단의 재원으로 지원을 받아 수행된 3단계 산학연협력 선도대학 육성사업(LINC 3.0)의 연구결과입니다. 이 연구는 2023년도 산업통상자원부 및 산업기술평가관리원(KEIT) 연구비 지원에 의한 연구임 (20013794/NTIS1415184586)

참고문헌

  1. B. D. Vos, A. Cuenen, V. Ross, H. Dirix, K. Brijs and T. Brijs, "The Effectiveness of an Intelligent Speed Assistance System with Real-Time Speeding Interventions for Truck Drivers: A Belgian Simulator Study," Sustainability, Vol.15, No.6, pp.5226, 2023. 
  2. M. P. Reddy, M. F. Mohiuddin, S. Budde, G. Jayanth, C. R. Prasad and S. Yalabaka, "A Deep Learning Model for Traffic Sign Detection and Recognition using Convolution Neural Network," 2022 2nd International Conference on Intelligent Technologies (CONIT), Hubli, India, pp.1-5, 2022. 
  3. S. Houben, J. Stallkamp, J. Salmen, M. Schlipsing and C. Igel, "Detection of Traffic Signs in Real-World Images: The {G}erman {T}raffic {S}ign {D}etection {B}enchmark," International Joint Conference on Neural Networks, No.1288, 2013. 
  4. F. Zaklouta, B. Stanciulescu, "Real-time traffic sign recognition in three stages," Robotics and autonomous systems, Vol.62, No.1, pp.16-24, 2014.  https://doi.org/10.1016/j.robot.2012.07.019
  5. S. Selcuk, S. Beker and O. F. Boyraz, "Development of a Traffic Speed Limit Sign Detection System Based on Yolov4 Network," Advances in Artificial Intelligence Research, Vol. 3, No.2, pp. 66-75, 2023.  https://doi.org/10.54569/aair.1184569
  6. Y. Zhu, W. Q. Yan, "Traffic sign recognition based on deep learning," Multimed Tools Applications, Vol.81, pp.17779-17791, 2022.  https://doi.org/10.1007/s11042-022-12163-0
  7. S. Gwak, H. Na, K. Kim, E. Song, S. Jeong, K. Lee, J. Jeong and S. Hwang, "Validation of Semantic Segmentation Dataset for Autonomous Driving," Journal of Drive and Control, Vol.19, No.4, pp.104-109, 2022.  https://doi.org/10.7839/KSFC.2022.19.4.104
  8. J. Lee, G. Gwak, K. Kim, W. Kang, D. Shin and S. Hwang, "Development of Virtual Simulator and Database for Deep Learning-based Object Detection," Journal of Drive and Control, Vol.18, No.4, pp.9-18, 2021.  https://doi.org/10.7839/KSFC.2021.18.4.009
  9. K. Kim, J. Lee, S. Gwak, W. Kang, D. Shin and S. Hwang, "Construction of Database for Deep Learning-based Occlusion Area Detection in the Virtual Environment," Journal of Drive and Control, Vol.19, No.3, pp.9-15, 2022.  https://doi.org/10.7839/KSFC.2022.19.3.009
  10. K. H. Park and O. S. Kwon, "Algorithm for Speed Sign Recognition Using Color Attributes and Selective Region of Interest," JBE Vol.23, No.1, 2018. 
  11. Y. Saadna, A. Behloul and S. Mezzoudj, "Speed limit sign detection and recognition system using SVM and MNIST datasets," Neural Computing & Applications, Vol.31, pp.5005-5015, 2019.  https://doi.org/10.1007/s00521-018-03994-w
  12. H. Wang, R. Yuan, H. Pan, W. Liu, Z. Xing, J. Huang, "Speed Sign Recognition in Complex Scenarios based on Deep Cascade Networks," IET Intelligent Transport Systems, Vol.14, No.6, pp.628-636, 2020.  https://doi.org/10.1049/iet-its.2019.0620
  13. S. Kong, J. Park, S. -S. Lee and S. J. Jang, "Lightweight Traffic Sign Recognition Algorithm based on Cascaded CNN," 2019 19th International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea (South), pp. 506-509, 2019. 
  14. J. Shen, H. Liao and L. Zheng, "A lightweight method for small scale traffic sign detection based on YOLOv4-Tiny," Multimed Tools Applications, 2023. 
  15. A. Zaibi, A. Ladghamand and A. Sakly, "A Lightweight Model for Traffic Sign Classification Based on Enhanced LeNet-5 Network," Journal of Sensors, Vol.2021, pp.13, 2021. 
  16. K. C. Ryu and Y. E. Kim, "An Analysis of Passenger Discomfort According to Vertical Vibration and Pitching," Transactions of KSAE, Vol.3, No.5, pp.100-110, 1995. 
  17. M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," arKiv preprint 1905.11946, 2020. 
  18. L. Deng, "The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]," IEEE Signal Processing Magazine, Vol.29, No.6, pp.141-142, 2012.  https://doi.org/10.1109/MSP.2012.2211477
  19. D. Yu, D. Kim, H. Choi and S. Hwang, "Hybrid Control Strategy for Autonmous Driving System using HD Map Information," Journal of Drive and Control, Vol.17, No.4, pp.80-86, 2020. https://doi.org/10.7839/KSFC.2020.17.4.080