http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Exploring Smoothing Techniques for Reliable Travel-Time Information in Probe-Based Systems
장진환,Jang, Jinhwan Intelligent Transportation Systems 2018 한국ITS학회논문지 Vol.17 No.1
하이패스 단말기의 확대 보급에 따라 DSRC 교통정보시스템이 지방부 도로를 중심으로 확대 설치되고 있다. 그러나 지방부 도로의 경우 고속도로와 달리 단말기 장착차량이 많지 않아 프로브 표본수가 충분하지 않는 경우가 종종 발생한다. 이 경우 프로브 통행시간은 적은 샘플수로 인해 많은 변동이 발생하고 이는 교통정보 오차를 증가시킨다. 본 연구는 부족한 샘플수로 인해 발생하는 통행시간 단기변동을 완화하여 신뢰성 있는 교통정보를 수집 제공하기 위해 프로브 통행시간 데이터에 이동평균, Loess, Savitzky-Golay 등 평활화 기법을 적용하였다. 그 결과, 낮은 샘플링(5%) 환경에서 통행시간 오차가 원시자료에 비해 45%까지 감소하는 결과를 보였다. 본 연구결과는 국내에서 운영 중인 프로브 기반 교통정보시스템에 적용되어 교통정보 신뢰도를 향상시킬 수 있을 것으로 기대된다. With the increasing popularity of electronic toll collection system using 5.8 GHz dedicated short-range communications (DSRC) technology, DSRC-based travel-time collection systems have been deployed on major urban and rural arterial routes in Korea. However, since probe sample sizes are frequently insufficient in probe-based systems, the gathered travel times from probe vehicles fluctuate significantly compared to those of the population; as a result, the accuracy of the collected travel times could decrease. To mitigate the fluctuations (also known as biases), smoothing techniques need to be applied. In this study, some smoothing techniques-moving average, the Loess, and Savitzky-Golay filtering-were applied to probe travel times. Resultantly, the error in the smoothed travel times at the lowest sampling plan (5%) decreased as much as 45% compared to those in non-smoothed travel times. The results of this study can be practically applied to probe-based travel-time estimation systems for providing reliable travel times along the travel corridor.
적외선 영상검지 기술을 활용한 고속도로 버스전용차로 단속시스템 개발
장진환,Jang, Jinhwan 한국ITS학회 2022 한국ITS학회논문지 Vol.21 No.5
An automatic freeway bus-only lane enforcement system was developed and assessed in a real-world environment. Observation of a bus-only lane on the Youngdong freeway, South Korea, revealed that approximately 99% of the vehicles violated the high-occupancy vehicle (HOV) lane regulation. However, the current enforcement by the police not only exhibits a low enforcement rate, but also induces unnecessary safety and delay concerns. Since vehicles with six passengers or higher are permitted to enter freeway bus-only lanes, identifying the number of passengers in a vehicle is a core technology required for a freeway bus-only lane enforcement system. To that end, infrared cameras and the You Only Look Once (YOLOv5) deep learning algorithm were utilized. For assessment of the performance of the developed system, two environments, including a controlled test-bed and a real-world freeway, were used. As a result, the performances under the test-bed and the real-world environments exhibited 7% and 8% errors, respectively, indicating satisfactory outcomes. The developed system would contribute to an efficient freeway bus-only lane operations as well as eliminate safety and delay concerns caused by the current manual enforcement procedures.