DOI QR코드

DOI QR Code

Development of Vehicle Classification Algorithm using Non-Contact Treadle Sensor for Toll Collect System

통행료징수시스템을 위한 무접점 답판 방식의 차종분류 알고리즘 개발

  • 서연곤 (전남대학교 전자컴퓨터공학과) ;
  • 류창국 (전남대학교 전자컴퓨터공학과) ;
  • 이배호 (전남대학교 전자컴퓨터공학부)
  • Received : 2016.10.20
  • Accepted : 2016.12.24
  • Published : 2016.12.31

Abstract

Vehicle classification system in domestic tollgates is usually to use treadle sensor for calculating wheel width and tread of the vehicle. Due to the impact that occurs when the wheels of the vehicle contact, treadle sensor requires high durability. Recently, KHC(Korea Highway Corporation) began operating high-speed lane for cargo truck. High-speed cargo truck generate more impact the design criteria of previous treadle. Therefore, an increase in the maintenance and management costs of the treadle damage is concerned. In this paper, we propose an algorithm to classify vehicles using non-contact treadle sensors for improving durability from physical impacts. This was based on the KHC's classification criteria and showed a classification accuracy of 99.5 % in one experiment with 1892 vehicles through Changwon tollgate in 1020 local road. Therefore, it shows that vehicle classification system using non-contact treadle sensor could be applied to domestic toll tollgates, effectively.

차량의 윤폭과 윤거 정보를 산출하는 답판 센서는 국내 유로 도로의 차종 분류 장치에서 일반적으로 사용 된다. 답판 센서는 차량 정보를 생성하기 위하여, 주행 중인 차랑의 바퀴와 접촉이 필요하며 따라서 이때 발생하는 충격을 견디기 위해 높은 내구성이 요구된다. 최근 한국도로공사가 요금소에서 화물차 고속 차로의 운영을 시작함에 따라, 화물차가 고속 주행할 때 발생하는 설계 기준 이상의 충격으로 인한 답판의 파손과 이에 따른 유지보수 및 관리 비용의 증가가 염려되고 있다. 본 논문에서는 물리적 충격에 대한 내구성을 향상 시킨 무접점 답판 센서를 사용해서, 통과 차량의 차종을 분류하는 알고리즘을 제안하였다. 이는 한국도로공사 6종 분류 방식을 기준으로 하였고, 지방도 1020호선의 창원 요금소를 통과하는 1892대를 대상으로 한 실험에서 99.5%의 분류 정확도를 나타내었고, 무접점 답판을 사용한 차종 분류 장치가 국내 유료 도로에 효과적으로 적용이 가능함을 확인하였다.

Keywords

References

  1. J. Oh, K. Jang, and M. Kim, "Improvement of Vehicle Classification Method using Vehicle Height Measurement," J. of the Korean Society of Road Engineers (KSRE), vol. 12, no. 4, Dec. 2010, pp. 47-51.
  2. S. Kwon and Y. Seo, "New Vehicle Classification Algorithm with Wandering Sensor," The J. of Korean Society of Transportation (JKST), vol. 27, no. 6, Dec. 2009, pp. 79-87.
  3. S. Cho, D. Lee, and S. Ruy, "A Study on Efficient Vehicle Classification based on 3-Piezo Sensor AVC SYSTEM," The J. of the Institute of Internet, Broadcasting and Communication (IIBC), vol. 13, no. 3, June 2013, pp. 25-31.
  4. S. Fazli, S. Mohammadi, and M. Rahmani, "Neural Network based Vehicle Classification for Intelligent Traffic Control," Int. J. of Software Engineering & Applications (IJSEA), vol. 3, no. 3, May 2012, pp. 17-22.
  5. S. Messelodi, C. Modena, and G. Cattoni, "Vision-based bicycle/motorcycle classification," Pattern Recognit. Lett, vol. 28, no. 13, Oct. 2007, pp. 1719-1726. https://doi.org/10.1016/j.patrec.2007.04.014
  6. T. Shin, "A vehicle classification system using a treadle for vehicle driving in multi-lane," Korean Intellectual Property Office (KIPO), Patent Application no. 10-2013-0089994, 30 July 2013.
  7. W. Zhang, Q. Wang, and C. Suo, "A Novel Vehicle Classification Using Embedded Strain Gauge Sensors," Int. J. of Sensors, vol. 8, no. 11, Nov. 2008, pp. 6952-6971. https://doi.org/10.3390/s8116952
  8. S. Jang and Y. Kim, "Vehicles classification apparatus of non contacting type," Korean Intellectual Property Office (KIPO), Patent Application no. 10-2012-0019455, 27 Feb. 2012.
  9. Y. Seo, C. Lew, and B, Lee, "Development of wheel width and tread acquisition algorithm using non-contact treadle sensor," J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 6, 2016, pp. 627-634. https://doi.org/10.13067/JKIECS.2016.11.6.627
  10. K. Jang and S. Kwak, "Fast Center Lane Detection Method for Vehicle Applications," J. of the Korea Institute of Electronic Communication Sciences, vol. 9, no. 6, 2014, pp. 649-656. https://doi.org/10.13067/JKIECS.2014.9.6.649
  11. K. Park and H. Kim, " A Study for Video-based Vehicle Surveillance on Outdoor Road," J. of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 11, 2013, pp. 1647-1653. https://doi.org/10.13067/JKIECS.2013.8.11.1647
  12. H. Kim, J. Park, K. Kim, and J. Do, "A Vehicle Detection and Tracking Algorithm Using Local Features of The Vehicle in Tunnel," J. of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 8, 2013, pp. 1179-1186. https://doi.org/10.13067/JKIECS.2013.8.8.1179