Pub Date : 2002-09-03DOI: 10.1109/ITSC.2002.1041232
I. Leefken
In this paper a method for scene representation in driver assistance applications is proposed. To gain noise reduction and unique environmental information detection object-hypotheses are evaluated. For each object an object-dynamic is built. The Object-dynamic consists of four one-dimensional neural fields for information evaluation of relative position, size and relative velocity. The chosen formulation enables fusion and separation of object-hypotheses gained from different sensors. Due to the dynamic character of the representation a reduction of noise and a prediction over short time periods is possible. The advantages of the representation are shown by inspecting real world sensor data.
{"title":"Scene representation for driver assistance by means of neural fields","authors":"I. Leefken","doi":"10.1109/ITSC.2002.1041232","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041232","url":null,"abstract":"In this paper a method for scene representation in driver assistance applications is proposed. To gain noise reduction and unique environmental information detection object-hypotheses are evaluated. For each object an object-dynamic is built. The Object-dynamic consists of four one-dimensional neural fields for information evaluation of relative position, size and relative velocity. The chosen formulation enables fusion and separation of object-hypotheses gained from different sensors. Due to the dynamic character of the representation a reduction of noise and a prediction over short time periods is possible. The advantages of the representation are shown by inspecting real world sensor data.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"148 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113984915","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.2002.1041214
Yu-Chiun Chiou, L. Lan
The conventional fuzzy logic controller (CFLC) is limited in application, because its logic rules and membership functions have to be preset with expert knowledge. To avoid such drawbacks, a genetic fuzzy logic controller (GFLC) is proposed by employing an iterative evolution algorithm to promote the learning performance of logic rules and the tuning effectiveness of membership functions from examples In sequence. In addition, an encoding method is developed to overcome the difficulties in dealing with numerous constraints while employing genetic algorithms in tuning membership functions. A case of GM car-following behaviors is experimented to verify the applicability and robustness of GFLC. The results demonstrate that GFLC can predict the car-following behaviors precisely. Due to the similarity between fuzzy neural networks (FNN) and GFLC, a comparison is also made and the results indicate that GFLC performs superior to FNN.
{"title":"Genetic fuzzy logic controllers","authors":"Yu-Chiun Chiou, L. Lan","doi":"10.1109/ITSC.2002.1041214","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041214","url":null,"abstract":"The conventional fuzzy logic controller (CFLC) is limited in application, because its logic rules and membership functions have to be preset with expert knowledge. To avoid such drawbacks, a genetic fuzzy logic controller (GFLC) is proposed by employing an iterative evolution algorithm to promote the learning performance of logic rules and the tuning effectiveness of membership functions from examples In sequence. In addition, an encoding method is developed to overcome the difficulties in dealing with numerous constraints while employing genetic algorithms in tuning membership functions. A case of GM car-following behaviors is experimented to verify the applicability and robustness of GFLC. The results demonstrate that GFLC can predict the car-following behaviors precisely. Due to the similarity between fuzzy neural networks (FNN) and GFLC, a comparison is also made and the results indicate that GFLC performs superior to FNN.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"45 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":"124025032","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.2002.1041290
Ling Yong, Caixia Li
Based on microscopic traffic models, the object-oriented method and visualization technology are applied to the microscopic simulation of urban traffic systems, and a concise and flexible traffic simulator is developed. For an urban traffic network with 3 by 3 intersections, simulation results show that the vehicle behaviors in the traffic network accord with human traffic experience, and the movement curves of vehicles reflect the response of drivers to many traffic events. The fixed time signal control scheme is also compared with the fuzzy logic one in the simulation. The proposed approach can be adopted to study general large-scale traffic networks.
{"title":"A microscopic simulator for urban traffic systems","authors":"Ling Yong, Caixia Li","doi":"10.1109/ITSC.2002.1041290","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041290","url":null,"abstract":"Based on microscopic traffic models, the object-oriented method and visualization technology are applied to the microscopic simulation of urban traffic systems, and a concise and flexible traffic simulator is developed. For an urban traffic network with 3 by 3 intersections, simulation results show that the vehicle behaviors in the traffic network accord with human traffic experience, and the movement curves of vehicles reflect the response of drivers to many traffic events. The fixed time signal control scheme is also compared with the fuzzy logic one in the simulation. The proposed approach can be adopted to study general large-scale traffic networks.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"219 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":"115973292","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.2002.1041320
Xu Ning, Zhiheng Li, Jingyan Song
Traffic flow data are dynamic and stochastic, which is one of its key characteristics.. The research on this characteristics is the basis of the research on the stability of traffic flow. Multiple methods are used in the process of traffic flow data. This article introduces the principle of profile of dynamic data. Using common data processing methods, this new data processing procedure visualizes the dynamic character of traffic flow data and brings in new methodology in traffic control, traffic data compression, traffic guidance and incident detection.
{"title":"A practical research on dynamic traffic flow data profile","authors":"Xu Ning, Zhiheng Li, Jingyan Song","doi":"10.1109/ITSC.2002.1041320","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041320","url":null,"abstract":"Traffic flow data are dynamic and stochastic, which is one of its key characteristics.. The research on this characteristics is the basis of the research on the stability of traffic flow. Multiple methods are used in the process of traffic flow data. This article introduces the principle of profile of dynamic data. Using common data processing methods, this new data processing procedure visualizes the dynamic character of traffic flow data and brings in new methodology in traffic control, traffic data compression, traffic guidance and incident detection.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"74 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":"126599756","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.2002.1041268
Jiang-tao Ren, X. Ou, Yi Zhang, Dongcheng Hu
Real-time network-level signal control, traffic assignment and route guidance are promising approaches for alleviating congestion. Different optimal sets of control parameters and strategies for area-wide signal control, traffic assignment and route guidance can be determined according to different traffic patterns using many methods. Because of the importance of pattern recognition of network-level traffic patterns in traffic control and other applications, we present some elementary research on the topic based on the theories and methods of pattern recognition. First, we formulate the general process of network-level traffic pattern recognition, then some useful methods, such as PCA and SVM, are used for feature extraction, training and classifying of network-level traffic patterns. The experimental results show that the effectiveness of the proposed methods.
{"title":"Research on network-level traffic pattern recognition","authors":"Jiang-tao Ren, X. Ou, Yi Zhang, Dongcheng Hu","doi":"10.1109/ITSC.2002.1041268","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041268","url":null,"abstract":"Real-time network-level signal control, traffic assignment and route guidance are promising approaches for alleviating congestion. Different optimal sets of control parameters and strategies for area-wide signal control, traffic assignment and route guidance can be determined according to different traffic patterns using many methods. Because of the importance of pattern recognition of network-level traffic patterns in traffic control and other applications, we present some elementary research on the topic based on the theories and methods of pattern recognition. First, we formulate the general process of network-level traffic pattern recognition, then some useful methods, such as PCA and SVM, are used for feature extraction, training and classifying of network-level traffic patterns. The experimental results show that the effectiveness of the proposed methods.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"20 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":"121854212","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.2002.1041302
J. Dillenburg, Ouri E. Wolfson, P. Nelson
The ultimate goal of the Intelligent Travel Assistant (ITA) is the fusion and development of a number of technologies into a device that will increase the efficiency of our transportation network through increased use of mass transit and ride sharing. The ITA will include: a) dynamic ridesharing, b) spatio-temporal database management, c) wireless communications, and d) a management framework. The ITA itself is envisioned to be a compact portable device with the capability to plan multi-modal routes for its user. The traveler will enter a desired destination into the ITA and it will formulate several plans to got the user to this destination. The ITA will make use of wireless Internet technology to send and receive traffic information, transit schedules, and arrange for payment of fares. The Global Positioning System (GPS) will be used to track the user's current position for use in route planning and also its it means of assessing traffic conditions while en-route. A spatio-temporal database management system will be used to efficiently track ITA positions in real-time.
{"title":"The Intelligent Travel Assistant","authors":"J. Dillenburg, Ouri E. Wolfson, P. Nelson","doi":"10.1109/ITSC.2002.1041302","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041302","url":null,"abstract":"The ultimate goal of the Intelligent Travel Assistant (ITA) is the fusion and development of a number of technologies into a device that will increase the efficiency of our transportation network through increased use of mass transit and ride sharing. The ITA will include: a) dynamic ridesharing, b) spatio-temporal database management, c) wireless communications, and d) a management framework. The ITA itself is envisioned to be a compact portable device with the capability to plan multi-modal routes for its user. The traveler will enter a desired destination into the ITA and it will formulate several plans to got the user to this destination. The ITA will make use of wireless Internet technology to send and receive traffic information, transit schedules, and arrange for payment of fares. The Global Positioning System (GPS) will be used to track the user's current position for use in route planning and also its it means of assessing traffic conditions while en-route. A spatio-temporal database management system will be used to efficiently track ITA positions in real-time.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"11 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":"121541090","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.2002.1041325
S. Clement, E.F.H. Ekner, Map Taylor
Dual-mode transport systems can be regarded as a hybrid of today's road transport system, some elements of the current crop of ITS technologies and personal rapid transit (PRT) systems. In this paper we compare the personal transport characteristics of today's system with an example-the simple platoon advancement (SPA) model-of future ITS deployment, and with PRT systems. Then we present dual-mode systems-for example the rapid urban flexible (RUF) system-as possessing characteristics of the above three systems.
{"title":"From cars towards dual-mode personal transport systems","authors":"S. Clement, E.F.H. Ekner, Map Taylor","doi":"10.1109/ITSC.2002.1041325","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041325","url":null,"abstract":"Dual-mode transport systems can be regarded as a hybrid of today's road transport system, some elements of the current crop of ITS technologies and personal rapid transit (PRT) systems. In this paper we compare the personal transport characteristics of today's system with an example-the simple platoon advancement (SPA) model-of future ITS deployment, and with PRT systems. Then we present dual-mode systems-for example the rapid urban flexible (RUF) system-as possessing characteristics of the above three systems.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"20 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":"125171561","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.2002.1041233
J. Yu, S. Peeta
The driver en-route route choice problem under real-time information is characterized by subjectively interpreted and/or linguistically expressed data on nonquantitative variables, as well as limited data on some quantitative variables. This paper proposes a hybrid fuzzy logit model to enable the treatment of nonquantitative and quantitative data simultaneously in a single framework to address the problem. Synergistically, its computational efficiency enables real-time deployment in a traffic control framework. The study highlights the appropriateness of using fuzzy variables to address recently identified en-route driver behavioral characteristics under information provision.
{"title":"A hybrid model for en-route driver behavior under real-time information","authors":"J. Yu, S. Peeta","doi":"10.1109/ITSC.2002.1041233","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041233","url":null,"abstract":"The driver en-route route choice problem under real-time information is characterized by subjectively interpreted and/or linguistically expressed data on nonquantitative variables, as well as limited data on some quantitative variables. This paper proposes a hybrid fuzzy logit model to enable the treatment of nonquantitative and quantitative data simultaneously in a single framework to address the problem. Synergistically, its computational efficiency enables real-time deployment in a traffic control framework. The study highlights the appropriateness of using fuzzy variables to address recently identified en-route driver behavioral characteristics under information provision.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"42 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":"115076324","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.2002.1041187
Zhijun Tang, U. Ozguner
As high-quality remote images become available for civilian applications, the idea of gathering traffic data from remote sensing has been proposed. One key issue in this area is how to track the vehicles through the remote image sequences. This paper describes an adaptive motion correspondence algorithm for multiple vehicle tracking from air-borne remote cameras. The motion correspondence is established by searching over an extended correspondence matrix. An on-line confidence factor is assigned to each track to control the search strategy. Experiments with real traffic scenarios showed that the algorithm could automatically distinguish track initiation from false detection, as well as track termination from occlusion, which demonstrated its feasibility for real-time applications.
{"title":"An adaptive motion correspondence algorithm for multiple vehicle tracking from an air-borne platform","authors":"Zhijun Tang, U. Ozguner","doi":"10.1109/ITSC.2002.1041187","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041187","url":null,"abstract":"As high-quality remote images become available for civilian applications, the idea of gathering traffic data from remote sensing has been proposed. One key issue in this area is how to track the vehicles through the remote image sequences. This paper describes an adaptive motion correspondence algorithm for multiple vehicle tracking from air-borne remote cameras. The motion correspondence is established by searching over an extended correspondence matrix. An on-line confidence factor is assigned to each track to control the search strategy. Experiments with real traffic scenarios showed that the algorithm could automatically distinguish track initiation from false detection, as well as track termination from occlusion, which demonstrated its feasibility for real-time applications.","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":"129955755","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.2002.1041291
Xu Yang, L. Chu, W. Recker
ALINEA, a local feedback ramp-metering strategy, has been shown to be a remarkably simple, highly efficient and easy application. This paper presents a microscopic simulation-based method to optimize the operational parameters of the algorithm, as an alternative to the difficult task of fine-tuning them in real-world testing. Four parameters, including the update cycle of the metering rate, a constant regulator, the location and desired occupancy of the downstream detector station, are considered. A genetic algorithm that searches the optimal combination of parameter values is employed. Simulation results show that the genetic algorithm is able to find a set of parameter values that can optimize the performance of the ALINEA algorithm.
{"title":"GA-based parameter optimization for the ALINEA ramp metering control","authors":"Xu Yang, L. Chu, W. Recker","doi":"10.1109/ITSC.2002.1041291","DOIUrl":"https://doi.org/10.1109/ITSC.2002.1041291","url":null,"abstract":"ALINEA, a local feedback ramp-metering strategy, has been shown to be a remarkably simple, highly efficient and easy application. This paper presents a microscopic simulation-based method to optimize the operational parameters of the algorithm, as an alternative to the difficult task of fine-tuning them in real-world testing. Four parameters, including the update cycle of the metering rate, a constant regulator, the location and desired occupancy of the downstream detector station, are considered. A genetic algorithm that searches the optimal combination of parameter values is employed. Simulation results show that the genetic algorithm is able to find a set of parameter values that can optimize the performance of the ALINEA algorithm.","PeriodicalId":365722,"journal":{"name":"Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems","volume":"11 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":"125731783","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：