한국ITS학회 논문지 (The Journal of The Korea Institute of Intelligent Transport Systems)

  • 제21권6호
  • /
  • Pages.87-96
  • /
  • 2022
  • /
  • 1738-0774(pISSN)
  • /
  • 2384-1729(eISSN)
한국ITS학회 (The Korea Institute of Intelligent Transport Systems)
권호 표지
DOI QR코드

DOI QR Code

스마트횡단시스템 활성화를 위한 교통약자의 횡단속도 추정

A Study on Estimating the Crossing Speed of Mobility Handicapped for the Activation of the Smart Crossing System

  • 김형규 (한국건설기술연구원 도로교통연구본부 ) ;
  • 변상철 (한국건설기술연구원 도로교통연구본부) ;
  • 윤여환 (한국건설기술연구원 도로교통연구본부 ) ;
  • 김재석 (한국건설기술연구원 도로교통연구본부 )
  • Hyung Kyu, Kim (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng. and building Technology) ;
  • Sang Cheal, Byun (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng. and building Technology) ;
  • Yeo Hwan, Yoon (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng. and building Technology) ;
  • Jae Seok, Kim (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng. and building Technology)
  • 투고 : 2022.10.14
  • 심사 : 2022.11.02
  • 발행 : 2022.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

고령보행자를 포함한 교통약자는 신체적 능력이 저하되어 보행속도가 상대적으로 낮으며, 인지반응시간이 느린 특성을 가지고 있지만, 현재 교통약자를 위한 보행신호는 0.8m/s로 일률적으로 적용하고 있다. 문제점을 개선하기 위하여 스마트 횡단시스템이 개발되어 운영되고 있지만, 보행자별 적정 보행속도를 반영한 신호운영이 이루어지지 못하고 있다. 본 연구에서는 교통약자비율이 높은 지역에서 수집된 영상정보를 활용하여, 교통약자의 종류, 보행자의 수, 도로의 기하구조 등을 고려한 신경망모형과 다중회귀모형기반의 횡단속도 추정모델을 개발하였다. 이를 통해 개발된 모델을 스마트횡단시스템에 적용하여 실시간 교통약자에 따른 최적 보행신호 제공을 지원하고자 하였다. 경기도 파주시의 도시 교통 네트워크에서 수집된 실제 교통 상황 데이터 2,400개를 사용하였다. 모델의 성능은 상관계수, 평균 절대오차 등 7개의 선택된 지표를 통해 평가되었다. 다중선형회귀모델은 상관 계수가 0.652이고 MAE가 0.182였으며, 신경망모델은 상관계수가 0.823이고 MAE가 0.105로 나타나. 신경망모델이 더 높은 예측력을 보였다.

The traffic vulnerable, including elderly pedestrians, have a relatively low walking speed and slow cognitive response time due to reduced physical ability. Although a smart crossing system has been developed and operated to improve problem, it is difficult to operate a signal that reflects the appropriate walking speed for each pedestrian. In this study, a neural network model and a multiple regression model-based traversing speed estimation model were developed using image information collected in an area with a high percentage of traffic vulnerability. to support the provision of optimal walking signals according to real-time traffic weakness. actual traffic data collected from the urban traffic network of Paju-si, Gyeonggi-do were used. The performance of the model was evaluated through seven selected indicators, including correlation coefficient and mean absolute error. The multiple linear regression model had a correlation coefficient of 0.652 and 0.182; the neural network model had a correlation coefficient of 0.823 and 0.105. The neural network model showed higher predictive power.

키워드

과제정보

본 연구는 파주시청 남북철도교통과 지원 사업으로 수행되었습니다(과제명 : 파주시 ITS 구축사업 사업관리 용역).

참고문헌

  1. Alhajyaseen, W. K. and Iryo-Asano, M.(2017), "Studying critical pedestrian behavioral changes for the safety assessment at signalized crosswalks", Safety Science, vol. 91, pp.351-360. https://doi.org/10.1016/j.ssci.2016.09.002
  2. American Association of State Highway and Transportation Officials(2011), A Policy on Geometric Design of Highways and Streets (6th ed.).
  3. Bansal, A., Goyal, T. and Sharma, U.(2019), "Modelling the pedestrian speed at signalised intersection crosswalks for heterogeneous traffic conditions", Promet-Traffic& Transportation, vol. 31, no. 6, pp.681-692. https://doi.org/10.7307/ptt.v31i6.3299
  4. Bendak, S., Alnaqbi, A. M., Alzarooni, M. Y., Aljanaahi, S. M. and Alsuwaidi, S. J.(2020), "Factors affecting pedestrian behaviors at signalized crosswalks: An empirical study", Journal of Safety Research, vol. 76, pp.269-275.
  5. Chang, C. Y., Woo, T. H. and Wang, S. F.(2011), "Analysis of pedestrian walking speeds at crosswalks in Taiwan", Journal of the Eastern Asia Society for Transportation Studies, vol. 9, pp.1186-1200.
  6. Fitzpatrick, K., Brewer, M. A. and Turner, S.(2006), "Another look at pedestrian walking speed", Transportation Research Record, vol. 1982, no. 1, pp.21-29. https://doi.org/10.1177/0361198106198200104
  7. Han, E., Cho, H. R., Mun, S. C., Yun, S. B. and Park, S. Y.(2020), "Improvement of Pedestrian Speed Criteria for the Pedestrian Green Interval at Silver Zone", The Journal of The Korea Institute of Intelligent Transport Systems, vol. 19, no. 4, pp.45-54. https://doi.org/10.12815/kits.2020.19.4.45
  8. Iryo-Asano, M. and Alhajyaseen, W. K.(2017), "Modeling pedestrian crossing speed profiles considering speed change behavior for the safety assessment of signalized intersections", Accident Analysis & Prevention, vol. 108, pp.332-342. https://doi.org/10.1016/j.aap.2017.08.028
  9. Korea National Police Agency(2012), Manual of Installation and Management of Traffic Signal.
  10. Tarawneh, M. S.(2001), "Evaluation of pedestrian speed in Jordan with investigation of some contributing factors", Journal of Safety Research, vol. 32, no. 2, pp.229-236. https://doi.org/10.1016/S0022-4375(01)00046-9