Accurate prediction of travel time is useful for car drivers, and thus it is critical to develop a prediction system to provide the information. AVI (Automatic Vehicle Identification) system has been developed as a direct and precise measurement tool, however, because of the constrains of the installation points, a few dozen systems have been installed so far. On the other hand, we have more than eighty thousand vehicle detectors which collect traffic volumes at each point every five minutes. We note that vehicle detectors are not quite adequate for the prediction of travel time since the traffic volume alone does not lead to the travel time. This paper proposes a new method of predicting travel time in real time using efficiently the data collected from the detectors. The route is divided into several sections. Then, the travel time of each section is estimated by the approximated velocity where the approximation is done via the time-varying coefficients autoregressive model. In order to evaluate this approach, several field experiments were carried out. The results show that predicted travel time closely approximates the measured value.

抄録全体を表示

今日, 交通管制システムにおける情報収集能力の高度化が求められるようになった. 従来の車両感知器は, 道路頭上に設置されたが主に使用され, 存在感知しか計測できなかった. そこで我々は, CCD カメラを用いた画像処理形の車両感知器を開発するにあたり, 1台のCCD カメラの映像から上り, 下りの車線上を走行する車両を認識し, 車種及び車体型式をリアルタイムで識別できる動画像処理アルゴリズムの開発を行った. その結果,各正答率は, 上り車線の車種識別が75%, 車体型式が75%, 下り車線の車種識別が80%, 車体型式識別が83%を得ることができた.

抄録全体を表示

車両感知器は信号制御等の基礎となる交通管制システムの中核装置である．そのため，精度の高いデータ収集が求められており，保守点検業務を定期的に行い，その機能の保全を行っている．車両感知器はデータ精度の低下を伴いながら故障する場合があり，また様々な交通環境にさらされるため，その検出に対して効果的かつ効率的な手法が求められている．著者らは交通量，占有時間を集約し，統計的な数値から異常を検出する手法を提案し，その有効性を確認した．本稿では交通環境が異なる3地域を抽出し，提案手法を適用し，結果を比較分析する．

抄録全体を表示

Since 1963 traffic information centers have been established in Japan to indicate the degree of congestion.
This congestion information is given by traffic policemen who observe with their eyes the queue length of vehicles at a signalized intersection and convert the length into one of the 5 rankings of degree of congestion. For the purpose of improving the accuracy and saving manpower, demand for automating the measurement has been increasing.
This paper describes the measuring procedure employed in the fully automated traffic information centers, in which the congestion degree is calculated by automatically checking the above-mentioned queue length with vehicle detectors.
In this method, queues can be measured by installing one or two vehicle detectors on the incoming path of an intersection and by reading out the time of occupancy by the detectors.
Since several typical values of the time of occupancy can be obtained depending on the relative distance between the position of the vehicle detector installed several hundred meters upstream from the stop line and the position of the end of the queue, a waiting queue-time of occupancy curve can be obtained.
By using this model we actually measured the congestion degrees, which were classified into four rankings, at several hundred intersections.
Within the range of zero to 1000m of queue length, the results obtained for the measured samples were 89% correct when a single vehicle detector was installed on one incoming path. When two vehicle detectors were installed on one incoming path. 96% of the measured samples were correct.
Since the measuring error is affected by bus stops, road engineering work, etc., the accuracy of measurement is expected to be further improved by minutely examining the installation sites of the vehicle detectors.

抄録全体を表示

Vehicle detectors play an indispensable role in traffic management and control systems (TMCS). The data collected via vehicle detectors are used to fulfill various functions such as signal control and traffic information provision. In Japan, TMCS use mainly ultrasonic detectors. Owing to their aged deterioration, their detection accuracy gradually reduces over many years, and thus their efficient operation and maintenance requires accomplished engineers. In recent years, it has become difficult to maintain great numbers of ultrasonic detectors because of the financial constraints in public resources and shortfall of accomplished engineers. In this paper, we propose failure detection methods, and confirm their validity by using actual data. First, we propose an aggregation method of detector data for classifying installation positions, and validate the method by using large amount of data. Moreover, we propose a few failure detection methods with the aggregated data, and compare their decision results by using the actual data.

抄録全体を表示

Vehicle detectors are required to operate in various environments. Current detectors employ various types of sensors including ultrasonic, loop coil, and image sensors. However, there exist some problems such as temperature and wind effects, maintenance problems, and accuracy degradation during nighttime. To solve these problems, we propose a vehicle detector that utilizes a 3D sensor based on near infrared laser and Time-of-Flight. This sensor can acquire a three-dimensional image that includes the distance data, unaffected by the external factors mentioned earlier. Therefore, our proposed vehicle detector design can be applied to traffic volume measurement, vehicle classification, multiple lane detection, etc. This paper discusses the application of the proposed vehicle detector in several scenarios.

抄録全体を表示

本研究は車両感知器データを用いた精度の高い所要時間の推定手法の開発を目的とした. はじめに個々の車両の走行軌跡を推定する手法を提案し, 従来から使われている瞬時値とタイムスライス値と比較した. また所要時間の推定精度の向上可能性について検討し, その結果をもとにセクションと時間インターバルを分割して, 分割されたそれぞれのセルに速度変動を考慮した速度データを割り当てて所要時間を推定する手法を提案した. また車線利用指数を用いて所要時間を推定する手法を提案した. その結果, 両手法ともに走行軌跡推定手法の推定誤差を大きく減少させることができた. 特に渋滞時において所要時間の推定精度を向上させることができた.

抄録全体を表示

パイプライン敷設工事や電線の地中化工事, 道路補修工事等のように道路を占用して行う工事では工事対象道路を通過する交通に大きな影響を与える。特に道路の片側全てを占用して工事を行う場合、通過交通は交互通行を強いられる。このように交互通行を行う場合、ガードマンや仮設信号によって交通制御が行われるが、人件費の高騰等から仮設信号により安全に効率よく交通を処理することが望ましい。しかしながら、従来の仮設信号では信号現示時間が固定されていることから、刻々と変化する道路交通を効率的に制御するこは困難である。そこで、本研究では交通量の変化に応じて信号機の現示パターンを自動的に変化させ得る動的制御を提案し、信号制御システムを開発するためのシミュレーションモデルを構築する。

抄録全体を表示

本記事に「抄録」はありません。

抄録全体を表示

本論文は, 画像処理の手法を利用して, 道路における交通状況を示す画像より自動車の部分を抽出し, その形状を自動識別する方法について述べている.自動車の車種を示す特徴はその輪郭形状, 特に自動車を側面から見た輪郭形状に最も良く現れる.このため本方式では, 2台のカメラを用いて自動車の3次元位置計測を行うが, 一台のカメラを車種識別用に自動車の側面を捉えるように設置し, 2台目のカメラを位置計測用に左斜め上方に設置する.これらの2台のカメラから得られた画像に対して計算機を用いて, 自動車の3次元位置の計測, モデルを用いた形状認識及び車種識別を行っている.

抄録全体を表示

Travel time is one of the most important traffic data. Although it has been studied to estimate it for a long time, there are still many problems about accuracy and measuring delay. So, we have developed an algorithm to match vehicles based on their characteristics, which are measurable by popular vehicle detectors and to estimate accurate travel time with short delay. As a result of evaluation, we demonstrate that this algorithm can estimate accurate travel time to be practical. Moreover, we improve this algorithm to be appropriate for practical use and evaluate it.

抄録全体を表示

車両感知器データを使って, 幹線道路における自動車排出ガス量を推計するシステムを開発した. 最初に, シャシダイナモメータによる排出ガス測定データを基に, 車の走行パターンから自動車排出ガス量を推定する方法を検討した. 次に, 実道路上での走行実態調査データと車両感知器データを用いて, 車両感知器データから走行パターンを推定する方法を検討した. 以上の検討結果を千葉県柏地域の国道16号, 国道6号, 県道船橋我孫子線に適用し, 238道路区間 (信号交差点に挟まれた区間) の排出ガス量を時々刻々と算出するシステムを構築した.

抄録全体を表示

The Information on travel time is useful to improve traffic efficiency, e.g., to reduce traffic congestion effectively. Travel time is computed from the passage time of vehicles observed at both origin (upstream) and destination (downstream) points. To do so, we are studying a vehicle identification method using vehicle height data obtained from ultrasonic vehicle detectors. However, matching method using vehicle height only, suffer from poor identification accuracy because many similar vehicles exist on the road. Therefore, we propose a method based on matching vehicle sequences (two or more vehicles). In addition, we develop this method using Genetic Algorithm based on traffic characteristic.

抄録全体を表示

The National Institute for Land and Infrastructure Management (NILIM) has been promoting R & D for the Advanced Cruise-Assist Highway Systems (AHS) that utilize roadside sensors and a traffic, driving simulator. The combination of AHS video sensors with a customized traffic, driving simulator realizes microscopic analyses of traffic behaviors that found diverse AHS services for improvement in traffic conditions. This paper introduces ongoing projects including successful one at FOT stage and the role of AHS as future approach that copes with drivers' characteristics against traffic accidents and congestion.

抄録全体を表示

本研究は、右折容量を車線数毎に算出し、片側二車線道路の信号交差点における現行の右折容量算出手法の問題点を明らかにしたものである。現行では、右折車の対向直進車の到着分布はポアソン分布であるとの前提に立って右折容量が算出されている。そして、対向直進車の台数に対応する右折確率は対向直進車の車線数に関係なく同じである。しかし、千葉県柏市周辺の道路で計測した結果、対向直進車の到着分布はポアソン分布ではないことが明らかであった。その結果として、対向直進車の車線数が2である場合には、右折確率は高くなった。また、右折容量を求める際には、二車線の対向直進車交通量の一車線への換算係数を0.73と提案した。

抄録全体を表示