Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041248
Dewang Chen, Xiaoyan Gong, C. Zheng
The importance of the traffic information collection system (TICS) in traffic control systems of urban freeways is analyzed. The advantages and disadvantages of some types of traffic detectors and data transmission methods are compared. For current TICS, wireless data transmission is suggested. In view of factors such as work principle, transmitting speed, and cost, the CDPD (Cellular Digital Packet Data) network is selected to transmit the traffic data. According to experimental results about the accuracy of RTMS (Remote Transportation Microwave Sensors) and data transmission experiments in Beijing freeways, the suggested scheme using RTMS and CPPD to compose TICS is feasible. Furthermore, the system structure and functional description of this wireless TICS are given.
分析了交通信息采集系统在城市高速公路交通控制系统中的重要性。比较了几种类型的交通检测器和数据传输方式的优缺点。对于目前的TICS，建议采用无线数据传输。考虑到工作原理、传输速度和成本等因素，选择CDPD (Cellular Digital Packet Data)网络来传输流量数据。根据RTMS (Remote Transportation Microwave Sensors)的精度实验结果和北京高速公路上的数据传输实验，提出了采用RTMS和CPPD组成TICS的方案是可行的。并给出了该无线检测系统的系统结构和功能描述。
{"title":"A wireless traffic information collection system in Beijing urban freeways","authors":"Dewang Chen, Xiaoyan Gong, C. Zheng","doi":"10.1109/ITSC.2002.1041248","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041248","url":null,"abstract":"The importance of the traffic information collection system (TICS) in traffic control systems of urban freeways is analyzed. The advantages and disadvantages of some types of traffic detectors and data transmission methods are compared. For current TICS, wireless data transmission is suggested. In view of factors such as work principle, transmitting speed, and cost, the CDPD (Cellular Digital Packet Data) network is selected to transmit the traffic data. According to experimental results about the accuracy of RTMS (Remote Transportation Microwave Sensors) and data transmission experiments in Beijing freeways, the suggested scheme using RTMS and CPPD to compose TICS is feasible. Furthermore, the system structure and functional description of this wireless TICS are given.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"647 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116413958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041260
F. Gaetani, R. Minciardi
A decentralized pure reactive scheme for dynamic route guidance of vehicles in an urban road network is proposed. The overall scheme is implemented through a set of decisional agents, one for each node at which different routing choices are possible. For each of such nodes an optimization problem is stated and solved, at the beginning of each interval time, whose objective is to determine the optimal splitting rates or vehicles incoming that node, for each possible final destination. The main objective of such a problem is to minimize the total travel time spent by each of the incoming vehicles. The overall control scheme is based on the solution of a single node optimal control problem. The coordination among the single node controllers is ensured by a procedure for information exchange.
{"title":"Dynamic models and optimal control methods for route guidance in urban traffic networks","authors":"F. Gaetani, R. Minciardi","doi":"10.1109/ITSC.2002.1041260","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041260","url":null,"abstract":"A decentralized pure reactive scheme for dynamic route guidance of vehicles in an urban road network is proposed. The overall scheme is implemented through a set of decisional agents, one for each node at which different routing choices are possible. For each of such nodes an optimization problem is stated and solved, at the beginning of each interval time, whose objective is to determine the optimal splitting rates or vehicles incoming that node, for each possible final destination. The main objective of such a problem is to minimize the total travel time spent by each of the incoming vehicles. The overall control scheme is based on the solution of a single node optimal control problem. The coordination among the single node controllers is ensured by a procedure for information exchange.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116602009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041335
A. Shalaby, A. Farhan
This paper explains a dynamic control system, which predicts deviations in bus operation and enables a transit controller to apply corrective control strategy prior to the actual occurrence of the variation. Two separated Kalman filter algorithms were used in the prediction-modeling framework of this system. Empirical Automatic Vehicle Location (AVL) and Automatic Passenger Counters (APC) data were used to develop the prediction model. The performance of the model was compared with previously developed models using the VISSIM traffic microsimulation package considering different operation scenarios.
{"title":"An integrated modeling system for dynamic operations control and real-time transit information","authors":"A. Shalaby, A. Farhan","doi":"10.1109/ITSC.2002.1041335","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041335","url":null,"abstract":"This paper explains a dynamic control system, which predicts deviations in bus operation and enables a transit controller to apply corrective control strategy prior to the actual occurrence of the variation. Two separated Kalman filter algorithms were used in the prediction-modeling framework of this system. Empirical Automatic Vehicle Location (AVL) and Automatic Passenger Counters (APC) data were used to develop the prediction model. The performance of the model was compared with previously developed models using the VISSIM traffic microsimulation package considering different operation scenarios.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123571697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041263
M. Abou Zeid, I. Chabini, E. Nam, A. Cappiello
Statistical acceleration and deceleration distributions are developed as a function of speed and road type. The approach allows for the estimation of acceleration and deceleration variation among vehicles on a link with a given speed. Acceleration is shown to be a random variable that follows a probabilistic distribution that is practically independent of the road type. For the given data set, this distribution is a half-normal distribution for both acceleration and deceleration. Moreover, the standard deviation of the distributions decreases as the speed range increases. The developed model has a number of applications, especially where acceleration needs to be modeled as in the case of non-microscopic traffic models. In such context, instantaneous emission models benefit most from this analysis as these models account for engine operation, accelerations, or other power surrogate terms, which lead to the generation of tailpipe emissions. Results of this paper also have applications for designing and validating regulatory driving cycles.
{"title":"Probabilistic modeling of acceleration in traffic networks as a function of speed and road type","authors":"M. Abou Zeid, I. Chabini, E. Nam, A. Cappiello","doi":"10.1109/ITSC.2002.1041263","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041263","url":null,"abstract":"Statistical acceleration and deceleration distributions are developed as a function of speed and road type. The approach allows for the estimation of acceleration and deceleration variation among vehicles on a link with a given speed. Acceleration is shown to be a random variable that follows a probabilistic distribution that is practically independent of the road type. For the given data set, this distribution is a half-normal distribution for both acceleration and deceleration. Moreover, the standard deviation of the distributions decreases as the speed range increases. The developed model has a number of applications, especially where acceleration needs to be modeled as in the case of non-microscopic traffic models. In such context, instantaneous emission models benefit most from this analysis as these models account for engine operation, accelerations, or other power surrogate terms, which lead to the generation of tailpipe emissions. Results of this paper also have applications for designing and validating regulatory driving cycles.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122623310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041316
S. Takahashi, H. Nakamura, H. Kazama, T. Fujikura
This paper describes offset optimization for the fluctuations of traffic flow using a genetic algorithm (GA). An offset, which is the target of signal control parameters for this study, is difficult to optimize because of its variety of combinations. Traffic signal optimization using GAs has has been investigated in previous studies, most of which focused on signal control without considering the fluctuations of traffic flow. In a practical situation, the rate of flow changes as time passes, so that offset optimization considering these fluctuations of flow is required. As a case study, an urban traffic route in a city of the Chubu region in Japan, with twenty-one signalized intersections, was tested. To perform offset-optimization by a GA, offset values were represented in a chromosome having the same number of genes as the signals. Two different schemes are introduced into the GA-based program and evaluated in terms of average travel time. The results show that the offset optimization schemes used in this study are valuable for efficient signal control.
{"title":"Genetic algorithm approach for adaptive offset optimization for the fluctuation of traffic flow","authors":"S. Takahashi, H. Nakamura, H. Kazama, T. Fujikura","doi":"10.1109/ITSC.2002.1041316","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041316","url":null,"abstract":"This paper describes offset optimization for the fluctuations of traffic flow using a genetic algorithm (GA). An offset, which is the target of signal control parameters for this study, is difficult to optimize because of its variety of combinations. Traffic signal optimization using GAs has has been investigated in previous studies, most of which focused on signal control without considering the fluctuations of traffic flow. In a practical situation, the rate of flow changes as time passes, so that offset optimization considering these fluctuations of flow is required. As a case study, an urban traffic route in a city of the Chubu region in Japan, with twenty-one signalized intersections, was tested. To perform offset-optimization by a GA, offset values were represented in a chromosome having the same number of genes as the signals. Two different schemes are introduced into the GA-based program and evaluated in terms of average travel time. The results show that the offset optimization schemes used in this study are valuable for efficient signal control.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127235535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041284
G. Kogut, M. Trivedi
In recent years, large number of cameras have been installed in freeway and road environments. While the use of some of these cameras is being automated through computer vision, few computer vision systems allow for true wide-area large scaled automation. This paper describes a distributed computing system capable of managing an arbitrarily large sensor network using only common computing and networking platforms. The architecture is capable of handling many common computer vision tasks, as well as the inter-sensor communication necessary for developing new algorithms which employ data from multiple sensors. This system is tested with an algorithm which tracks moving objects through a prototype camera network with non-overlapping fields or view in a college campus environment This algorithm allows the system to maintain the identity of a tracked objects as it leaves and enters the fields of view of individual sensors. Such an algorithm is necessary for applications which require tracking objects over large distances or over long periods of time in an environment without complete sensor coverage.
{"title":"Real-time wide area tracking: hardware and software infrastructure","authors":"G. Kogut, M. Trivedi","doi":"10.1109/ITSC.2002.1041284","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041284","url":null,"abstract":"In recent years, large number of cameras have been installed in freeway and road environments. While the use of some of these cameras is being automated through computer vision, few computer vision systems allow for true wide-area large scaled automation. This paper describes a distributed computing system capable of managing an arbitrarily large sensor network using only common computing and networking platforms. The architecture is capable of handling many common computer vision tasks, as well as the inter-sensor communication necessary for developing new algorithms which employ data from multiple sensors. This system is tested with an algorithm which tracks moving objects through a prototype camera network with non-overlapping fields or view in a college campus environment This algorithm allows the system to maintain the identity of a tracked objects as it leaves and enters the fields of view of individual sensors. Such an algorithm is necessary for applications which require tracking objects over large distances or over long periods of time in an environment without complete sensor coverage.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126338813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041265
N. Grier, I. Chabini
We consider the problem of finding one to all minimum time paths for all departure times in a FIFO time dependent network with discrete arc travel times. We suggest that the problem can be viewed as a series of reoptimization of shortest path trees in static networks. This is accomplished via the concept of projection. We propose an algorithm which utilizes these projections to solve the one to all shortest path problem in a dynamic network. This algorithm is unique from an operational perspective as it only requires minimum data in advance.
{"title":"A new approach to compute minimum time path trees in FIFO time dependent networks","authors":"N. Grier, I. Chabini","doi":"10.1109/ITSC.2002.1041265","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041265","url":null,"abstract":"We consider the problem of finding one to all minimum time paths for all departure times in a FIFO time dependent network with discrete arc travel times. We suggest that the problem can be viewed as a series of reoptimization of shortest path trees in static networks. This is accomplished via the concept of projection. We propose an algorithm which utilizes these projections to solve the one to all shortest path problem in a dynamic network. This algorithm is unique from an operational perspective as it only requires minimum data in advance.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116899556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041209
Xia Liu, Youding Zhu, K. Fujimura
Driver pose estimation is one of the key components for future driver assistance systems since driver pose contains much information about his driving condition such as attention and fatigue levels. To this goal, a system is presented that detects the pose of the driver face in real time under realistic lighting conditions. The goal of the work is to automate the training phase, thereby eliminating the process of entering user information as much as possible. Two learning methods are presented for driver pose estimation. The first method uses unsupervised learning with Kohonen competitive networks, while the second method explores SVR with an appearance-based method.
{"title":"Real-time pose classification for driver monitoring","authors":"Xia Liu, Youding Zhu, K. Fujimura","doi":"10.1109/ITSC.2002.1041209","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041209","url":null,"abstract":"Driver pose estimation is one of the key components for future driver assistance systems since driver pose contains much information about his driving condition such as attention and fatigue levels. To this goal, a system is presented that detects the pose of the driver face in real time under realistic lighting conditions. The goal of the work is to automate the training phase, thereby eliminating the process of entering user information as much as possible. Two learning methods are presented for driver pose estimation. The first method uses unsupervised learning with Kohonen competitive networks, while the second method explores SVR with an appearance-based method.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131042639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041338
W. Oertel, T. Dimter, Daniel Dipl.-Verkehrsw. Szoska
The paper presents a stationary system developed for automatic supervision of railway station platforms, especially under conditions of automated train operation. It uses cameras mounted at the platform and supervision computers analyzing the camera data to detect persons or obstacles in different platform areas. The paper starts with a review of the state of the art and derives the system task and approach. Then, an overview of the system is given with its hardware and software technology, image processing, and operational surroundings. Practical test results and an evaluation conclude the paper.
{"title":"A video-based approach for stationary platform supervision","authors":"W. Oertel, T. Dimter, Daniel Dipl.-Verkehrsw. Szoska","doi":"10.1109/ITSC.2002.1041338","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041338","url":null,"abstract":"The paper presents a stationary system developed for automatic supervision of railway station platforms, especially under conditions of automated train operation. It uses cameras mounted at the platform and supervision computers analyzing the camera data to detect persons or obstacles in different platform areas. The paper starts with a review of the state of the art and derives the system task and approach. Then, an overview of the system is given with its hardware and software technology, image processing, and operational surroundings. Practical test results and an evaluation conclude the paper.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126811688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041329
Mark Hickman
Automatic vehicle location (AVL) data can be used for a variety of operational and planning purposes at a transit agency. One possible application is for passenger itinerary planning, where the passenger seeks to go from an origin to a destination in some "optimal" way. The AVL data give actual vehicle arrival and departure times, which in turn can give more robust itineraries to passengers. A method to determine such robust itineraries is described, and an example of the bus network in Tucson, Arizona (USA) is used to illustrate the method. Advantages of this method over traditional itinerary planning methods are also outlined.
{"title":"Robust passenger itinerary planning using transit AVL data","authors":"Mark Hickman","doi":"10.1109/ITSC.2002.1041329","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041329","url":null,"abstract":"Automatic vehicle location (AVL) data can be used for a variety of operational and planning purposes at a transit agency. One possible application is for passenger itinerary planning, where the passenger seeks to go from an origin to a destination in some \"optimal\" way. The AVL data give actual vehicle arrival and departure times, which in turn can give more robust itineraries to passengers. A method to determine such robust itineraries is described, and an example of the bus network in Tucson, Arizona (USA) is used to illustrate the method. Advantages of this method over traditional itinerary planning methods are also outlined.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132210741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：