Search

This article proposes a method of estimating the concentrations of particulate matter (PM2.5 and PM10) using public data, including road-traffic closed-circuit television (CCTV) images, Smart Seoul City data sensor environment information, and Korea Meteorological Administration data. The region-of-interest images and full scenes derived from CCTV footage were used as the basis for the deep learning model, which combines a convolutional neural network and long short-term memory, to establish the particulate matter (PM) concentration prediction methodology. In the experiment, the prediction accuracies corresponding to various types of mean values were calculated by training the model with various mean measurement values for the surface PM2.5 and PM10 concentrations, as well as the corresponding CCTV images and weather data at different time points. In the experiments performed under relatively stable PM concentrations, R2 generally exceeded 0.9 and tended to increase with an increasing range of mean concentration values. In particular, in sections with rapid changes in the PM concentration within an hourly interval, higher R2 values were obtained by the model trained with the average PM concentrations of the time series before and after image capture, outperforming the method that used prior mean observation values and better reflecting the current PM concentration.

Until now, studies on ensuring the safety of autonomous vehicles have been undergoing many trials and errors. Especially, the environmental analysis for autonomous driving in bad weather conditions such as snow, rain, fog, etc. has many problems due to the observation limit of the autonomous sensor equipment. In this paper, we propose a system for estimating precipitation information using radar sensor data, which is one of the important factors of the driving environment. The method consists of a filtering method to remove objects and a rainfall detection technology by estimating qualitative rainfall intensity. Test results in real driving and rain conditions confirm that the proposed system is working properly.

As a strategy to enhance traffic management, roundabouts come to the fore recently to decrease traffic accidents, streamline traffic flows, and expedite the realization of green transportation. As local governments introduced roundabouts, new road sign standards have to be established because the existing road sign regulations cannot be applied to roundabouts. Prior to trying to make suitable specification of sub-destination signs in roundabouts, regulations of other countries were examined and modified. The legend and location was calculated so that drivers could turn in time. Two specifications were determined by simulation experiments. As a result, drivers could read signs at right side better than at traffic island, and turn in time at 15cm legend size. Consequently, we proposed the minimum specifications and optimal locations of sub-destination signs.최근 교통운영체계 선진화방안의 일환으로 사고감소 , 소통증진, 저탄소 녹색교통 활성화 차원에서 회전교차로의 도입 필요성이 대두되고 있다 . 지자체에서는 회전교차로 설치사업을 추진함에 따라 회전교차로의 도입이 점차 확대되고 있으나, 현 도로표지 설치 기준에 따라 보조방향표지를 설치할 경우 교차로의 형태에 적합하지 않아 그 설치기준을 새롭게 마련할 필요가 있다. 따라서, 본 연구에서는 국내 회전교차로의 도로표지 설치 기준을 실험을 통해 도출하고자 하였다. 국외 회전교차로의 도로표지 설치 기준에 대해 고찰하여 규격 및 설치위치에 대한 사항을 준용하여, 교차로 내에서 적정 위치에서 회전할 수 있도록 설치위치 및 최소 글씨크기를 산출하여 적용하였다 . 설치 가능한 위치별 2개의 규격을 적용하였으며 , 시뮬레이터를 이용한 실험을 실시하였다 . 실험결과에 따라, 운전자가 인지와 판독이 용이한 위치는 우측부였으며 , 최소글씨 크기 15cm 일 때 원하는 출구로 진출이 가능하였다 . 이에 따라, 회전교차로에 설치되는 보조방향표지의 최소 글씨크기 및 설치위치에 대한 기준을 도출하였다 .

Road signs serve guide informations for efficient traffic control and are regulated by Road Sign Regulation. But few road managers break the regulation because of civil complaint and cause driver`s confusion. Also, as promote the road name guide signs and the new road signs on expressway, the driver`s confusion being increased. This study analysis factors of driver`s confusion, calculates limited information on road signs and specifies modes of driver`s confusion caused by road signs. The traffic accident data during 3 years is calculated in order to see how much intimate connection between the road sign confusion and the traffic.