Archives Search

Abstract

This paper reports on the results of the SINTEF Driving Simulator study of behavioural adaptation to the Adaptive Front-Lighting System (AFS). The main focus of the study was to supplement previous CLARESCO trials, and investigate to what extend driver behaviour change as...Lead moreThis paper reports on the results of the SINTEF Driving Simulator study of behavioural adaptation to the Adaptive Front-Lighting System (AFS). The main focus of the study was to supplement previous CLARESCO trials, and investigate to what extend driver behaviour change as a function of experience. Further, this effort aims to provide description of possible patterns of driving with AFS versus control group in deiffernt traffic environments. 40 drivers were exposed to approximately 140 kilometres of driving over six days in the SINTEF Driving Simulator. The scenarios combined City and rural country road environments In conclusion, the results of this study suggest that there is a behavioral adaptation to AFS in terms of speed choice with increase in speed after the initial familiarization (novelty fase), but not for the other selected indicators of behavioural adaptation. There is a general speed increase in both City and Rural environments from day one to six, but the increase is le

Abstract

Emerging driver assistance systems, such as look-ahead cruise controllers for heavy duty vehicles, require high precision digital maps. This contribution presents a road grade estimation algorithm for fusion of GPS and vehicle real-time sensor data, with measurements from...Lead moreEmerging driver assistance systems, such as look-ahead cruise controllers for heavy duty vehicles, require high precision digital maps. This contribution presents a road grade estimation algorithm for fusion of GPS and vehicle real-time sensor data, with measurements from previous runs over the same road segment. The resulting road grade estimate is thus enhanced using measurements from additional traversals of known roads. Distributed data fusion is utilized to ensure that the storage requirement of known roads does not increase when additional measurements are processed. The implemented algorithm, which is based on extended Kalman filtering and smoothing, is described in detail. Experiments on a Scania test vehicle show the advantages and some of the challenges with the proposed approach.

Abstract

This study explores the congestion dependence relationship among links using microsimulation, based on data from a real road network. The work is motivated by recent innovations to improve the reliability of Dynamic Route Guidance (DRG) systems. By adding a function to pr...Lead moreThis study explores the congestion dependence relationship among links using microsimulation, based on data from a real road network. The work is motivated by recent innovations to improve the reliability of Dynamic Route Guidance (DRG) systems. By adding a function to predict the congestion in the road network, the reliability of DRG systems can be significantly enhanced. The identification of link congestion dependence patterns is considered to be the first step towards this target. Previous work on link reliability and failure dependence relationships is reviewed and the results of simulation and analysis are presented here.

Abstract

This study develops a hybrid model that can reliably estimate travel times on freeways with sparsely distributed detectors having the spacing of more than one mile. The developed model, which includes a clustered linear regression model as the main component and a supplem...Lead moreThis study develops a hybrid model that can reliably estimate travel times on freeways with sparsely distributed detectors having the spacing of more than one mile. The developed model, which includes a clustered linear regression model as the main component and a supplemental enhanced trajectory-based model, can effectively capture impacts of various geometric features, such as ramps and merging lanes, and different traffic patterns on the variability of travel times. The experimental results based on a field demonstration on a 25-mile stretch of I-70 eastbound with 10 detectors have demonstrated the promising properties of the developed model under various congestion levels.

Abstract

Over the last two decades travel time reliability has become an important aspect of transportation system performance. One group of factors affecting travel time variability is dynamic traffic control measures, such as dynamic speed limit. Knowing how dynamic speed limit ...Lead moreOver the last two decades travel time reliability has become an important aspect of transportation system performance. One group of factors affecting travel time variability is dynamic traffic control measures, such as dynamic speed limit. Knowing how dynamic speed limit influenced on travel time variability can help improve travel time reliability. Empirical investigation on the basis of a large database of travel times on two freeway corridors shows that travel time variability is strongly affected by dynamic speed limit. Above a certain threshold inflow, Critical Transition inFlow CTF, dynamic speed limit contributes to more reliable travel time. Below CTF, dynamic speed limit, however, leads to higher travel time variability. Dynamic speed limit results in higher CTF due to the fact of homogenization of traffic flow and the prevention of traffic breakdown on the use of dynamic speed limit.

Abstract

This paper presents an analytical investigation of modeling departure time choice under stochastic capacity with Vickrey’s bottleneck model. The deterministic bottleneck model of Vickrey has been extended with random capacities. It is assumed that travelers are fully awar...Lead moreThis paper presents an analytical investigation of modeling departure time choice under stochastic capacity with Vickrey’s bottleneck model. The deterministic bottleneck model of Vickrey has been extended with random capacities. It is assumed that travelers are fully aware of the stochastic properties of the travel time and schedule delays at all departure times that emerge from day-to-day due to random capacity. Long term equilibrium is achieved under stochastic capacities. Based on the analytical analyses, consideration of random capacities and travel time reliability in the utility function results into significant shifts in the temporal demand pattern. Travelers depart earlier and departure flows become more spread over a longer time period. The maximum queue is less and the maximum travel time is less. These theoretical findings are supported by empirical findings of delays at bottlenecks.

Abstract

We present an immersive video system that has been developed for the purpose of evaluating future traveller information system (FTIS). In particular, FTIS scenarios that rely on a pervasive computing infrastructure. Immersive video uses multiple video streams captured fro...Lead moreWe present an immersive video system that has been developed for the purpose of evaluating future traveller information system (FTIS). In particular, FTIS scenarios that rely on a pervasive computing infrastructure. Immersive video uses multiple video streams captured from a first person perspective at key locations in a scenario. By dynamically reconstructing a user’s visual and aural experiences the immersive video system creates a lab-based framework that captures a number of the contextual factors of real-world mobile information system use. Graphical user interfaces, displayed on a personal digital assistant (PDA) and a wearable display, are used in a preliminary evaluation of FTIS. We present both the technical basis of the immersive video system and its application to the study of user perceptions and reactions to pervasive information services.

Abstract

This paper deals with the detection of circular traffic signs, such as prohibition sign, obligation sign and etc. Compared with the existing methods, our method has the following characters: Firstly certain color and shape characters are enhanced to emphasize traffic sign...Lead moreThis paper deals with the detection of circular traffic signs, such as prohibition sign, obligation sign and etc. Compared with the existing methods, our method has the following characters: Firstly certain color and shape characters are enhanced to emphasize traffic sign region; Secondly, newly proposed gradient information based Hough transform is followed to estimate circle centre and radius, which can greatly decrease computation load; Finally, integration and projection method is adopted to extract the precise region of traffic sign. Experiments show that our method is efficient to detect circular traffic signs and can be used in real time system

Abstract

In order to assist driver's vision, a real-time recognition system for traffic signs is proposed. After detecting sign candidates, biologically inspired opponent-color filters are used to extract the symbol parts of signs. After normalizing the size of symbols, structural...Lead moreIn order to assist driver's vision, a real-time recognition system for traffic signs is proposed. After detecting sign candidates, biologically inspired opponent-color filters are used to extract the symbol parts of signs. After normalizing the size of symbols, structural features are calculated to identify signs. In total, 5572 segmented images are used to design the algorithm and 98% recognition rate could be attained. In a real-time system, the same sign in a sequence of frames is tracked and recognized, and majority vote is used to integrate the recognition obtained in each frame. Recognition rate of 99% could be attained for test data.

Abstract

More than 50% of congestion occurs in uninterrupted flow sections of sag or upgrade slope and tunnel entrance on intercity expressways in Japan. It is urgent and important to take cost-effective soft measures to mitigate traffic congestion. Based on the result of several ...Lead moreMore than 50% of congestion occurs in uninterrupted flow sections of sag or upgrade slope and tunnel entrance on intercity expressways in Japan. It is urgent and important to take cost-effective soft measures to mitigate traffic congestion. Based on the result of several experiments by providing bottleneck location information with simple variable message sign, this study aims to evaluate the effect of the variable message sign on increase of bottleneck capacity. As a result, observed queue discharge flow rate is increased by 5-15%, which could recover 25% to nearly 90% of capacity drop after congestion depending upon bottleneck. A mechanism is described from the viewpoint of drivers’ behavior. The increase of pre-queue breakdown flow rate could also be expected sometimes.

Abstract

Propagation characteristics for inter-vehicle communication using the 76-GHz band are measured. Direct wave and one-time wave reflection from the road surface are dominant factors affecting inter-vehicle millimeter-wave communication systems. The interference between dire...Lead morePropagation characteristics for inter-vehicle communication using the 76-GHz band are measured. Direct wave and one-time wave reflection from the road surface are dominant factors affecting inter-vehicle millimeter-wave communication systems. The interference between direct waves and reflection waves causes considerable fluctuation in the received power. The vehicle vibration can be ignored with regard to its effect on millimeter-wave propagation. The road surface, however, strongly influences the interference pattern. Attenuation by rain is another factor affecting signal propagation for inter-vehicle millimeter-wave communication. The attenuation caused by raindrops is especially great near the road surface because of the rebound of raindrops. These results will be useful for determining the link budget of inter-vehicle communication systems that use the 76-GHz band

Abstract

This paper formulates the problem of fusing travel time from cameras with speeds from inductive loops. By using a simple recursive algorithm, vehicle trajectories are step-by-step approached. The performance of this algorithm is validated and evaluated in a synthetic environment.This paper formulates the problem of fusing travel time from cameras with speeds from inductive loops. By using a simple recursive algorithm, vehicle trajectories are step-by-step approached. The performance of this algorithm is validated and evaluated in a synthetic environment.

Abstract

Public transit network is different from general road network. The bus stop’s passenger flow and buses’ limited capacity show more impacts on bus running time than road traffic flow. So the conventional public transit models assignment adopting ecumenic road network path ...Lead morePublic transit network is different from general road network. The bus stop’s passenger flow and buses’ limited capacity show more impacts on bus running time than road traffic flow. So the conventional public transit models assignment adopting ecumenic road network path concept have many limitations. Based on the analysis, the generalized bus trip time chain is analyzed, and the concept of congestion function is proposed to describe the relation between trip resistance and flow in this paper. On the basis of these study, transit network resistance function is formed, then the multi-route probit-based loading model is established and the algorithm is analyzed. At last, the model is applied to the transit network assignment of Yangzhou. The example indicates that the model can provide the practical operation with a high precision result.

Abstract

Road pricing (RP) is regarded as the most effective measure to solve the traffic congestion in urban areas, but the difficulty of forming a consensus among the stakeholders has become an obstacle to the implementation of RP in Japan. Nagoya University has proposed a “Park...Lead moreRoad pricing (RP) is regarded as the most effective measure to solve the traffic congestion in urban areas, but the difficulty of forming a consensus among the stakeholders has become an obstacle to the implementation of RP in Japan. Nagoya University has proposed a “Parking Deposit System” (PDS) as a new form of road pricing to which the public would be greatly receptive, and is studying the possibility of implementing such a system through industry-government-academia collaboration. In 2008 the university intends to conduct a pilot program in the city of Nagoya prior to implementation to verify empirically the acceptability and benefits of introducing PDS. Ahead of this program, a questionnaire survey of visitors to downtown Nagoya was conducted in November 2006 to ascertain the acceptability of PDS. This paper discusses a) the advantages of PDS from an acceptability perspective and b) changes in travel behavior stemming from PDS, as indicated by the survey results.

Abstract

Bus Rapid Transit (BRT) has been considered as a promising alternative of public transportation system that combines service quality of rail system and operation flexibility of bus transit system. It consists of many features such as dedicated right of way, signal priorit...Lead moreBus Rapid Transit (BRT) has been considered as a promising alternative of public transportation system that combines service quality of rail system and operation flexibility of bus transit system. It consists of many features such as dedicated right of way, signal priority, cleaner and quieter vehicles, rapid and convenient fare collection, Intelligent Transportation System (ITS) technologies and integration with land use policy. In recent years many BRT systems have been proposed and implemented. However, there is a lack of systematic approach to incorporate ITS planning and design into BRT system development. This study proposes a method for selecting appropriate ITS technologies in BRT system. This paper first identifies ITS technologies and related function needs for BRT system and then develops a methodology based on Analytic Hierarchy Process and Expert System to help of selecting the suitable combinations of ITS technologies that can provide synergies to enhance service quality

Abstract

Travel Information System (TIS), which is the early stage of Advanced Traveler System (ATIS), suits the situation in some developing countries for its less cost and rapid result. China, as one of the developing countries, also has a brilliant prospect in implementing TIS....Lead moreTravel Information System (TIS), which is the early stage of Advanced Traveler System (ATIS), suits the situation in some developing countries for its less cost and rapid result. China, as one of the developing countries, also has a brilliant prospect in implementing TIS. Therefore, the method of planning a TIS for a highway in China was researched. The return indicates that the plan method can be divided into 11 steps, including project feasibility analysis, travel information service status investigation, project objective identification, travel information requirement survey, user service determination, logic architecture design, physical architecture design, application project composition, application design, plan evaluation and plan amendment. The operation process of each step was also worked out. This experience can be shared with the designers in the other developing countries.

Abstract

In contrast to traditional traffic sensors like induction loops, the position data from fleets of Probe Vehicles are an excellent technology to determine travel times which are needed for information and route guidance systems. This contribution describes an application o...Lead moreIn contrast to traditional traffic sensors like induction loops, the position data from fleets of Probe Vehicles are an excellent technology to determine travel times which are needed for information and route guidance systems. This contribution describes an application of a taxi-PVD system in Hamburg with about 700 taxis. Here, an information system was set up which delivers travel times accessible via internet. The information is validated with test drives of independent vehicles driving on the routes. It is demonstrated that a taxi-PVD system like this is able to deliver reliable information about travel times.

Abstract

In Japan, about 50% of the traffic accidental death is considered as caused by the "delay of discovery" of crossing cars and pedestrians. Since a driver's vision is easily obscured by buildings at crossroads, we developed a brand-new Java3D-based driving simulator which c...Lead moreIn Japan, about 50% of the traffic accidental death is considered as caused by the "delay of discovery" of crossing cars and pedestrians. Since a driver's vision is easily obscured by buildings at crossroads, we developed a brand-new Java3D-based driving simulator which can generate the "virtual sound image" of invisible approaching cars. The Java3D enables us to handle the both of 3D graphics and 3D sound simultaneously. So we could compose a cost-effective and flexible Virtual Sound Imaging System on a personal computer which is equipped with plural displays. We confirmed the fundamental effectiveness of the Virtual Sound Image using the Java3D-based driving simulator.

Abstract

Short-term prediction of traffic conditions is one of the central topics in contemporary ITS research and practice. However, it is hard to select the most appropriate traffic prediction method for one particular application. In this paper we aim to provide taxonomy of all...Lead moreShort-term prediction of traffic conditions is one of the central topics in contemporary ITS research and practice. However, it is hard to select the most appropriate traffic prediction method for one particular application. In this paper we aim to provide taxonomy of all different approaches reported in literature as a practical reference for ITS professionals and researchers. It is concluded that apart from traffic simulation models only few methods are used for network wide predictions, while this is necessary for most practical applications (e.g. in-car navigation). Second, there appears to be no single best method. It is suggested that instead of developing more methods future research should focus on combining models into one network wide application.

Abstract

This paper introduced a new intelligent bus-dispatching strategy, which based on the static and dynamic dispatching rules corresponding to the common transit status and emergencies. In particular, this paper addressed the establishment of Dispatching Rule Base, which can ...Lead moreThis paper introduced a new intelligent bus-dispatching strategy, which based on the static and dynamic dispatching rules corresponding to the common transit status and emergencies. In particular, this paper addressed the establishment of Dispatching Rule Base, which can absorb many excellent dispatching methods to make timely and efficient dispatching of buses. Moreover, an intelligent bus-dispatching system was set up, including the Dispatching Rule Base, the Vehicle Monitoring Database and the Timetable for Static Dispatching. The achieved results of simulation experiments on actual transit routes have proved the feasibility and validity of dispatching rules.

Abstract

In this paper, based on mobile phone locating, a new method for estimating real-time traffic variables on freeway is presented. Mobile phones have become a common personal communication tool all over the world. Therefore, the limitation of sample size and coverage associa...Lead moreIn this paper, based on mobile phone locating, a new method for estimating real-time traffic variables on freeway is presented. Mobile phones have become a common personal communication tool all over the world. Therefore, the limitation of sample size and coverage associated with data collection is no longer an issue. In the proposed method, the state of vehicles on freeway is estimated by clustering and analyzing the location, speed and acceleration of the mobile phones carried on vehicles. Then traffic variables are calculated from the state of separate vehicles. It can estimate traffic variables in the condition of wide range, low cost and high efficiency.

Abstract

This paper describes the methodology of the long-term survey within the Flemish research program “An activity-based approach for surveying and modelling travel behaviour”. During one year, travel and driving behaviour of 30 respondents will be monitored. The methodology c...Lead moreThis paper describes the methodology of the long-term survey within the Flemish research program “An activity-based approach for surveying and modelling travel behaviour”. During one year, travel and driving behaviour of 30 respondents will be monitored. The methodology consists of using an on-board vehicle device and a web-application. The on-board device is equipped with a GPRS-modem, a GPS system and a CAN-interface. The GPS system allows to monitor travel behaviour. Driving behaviour will be studied by logging various CAN-parameters (e.g. revs per minute, chosen gear etc). Data will be transmitted to a central server with the GPRS-network. Respondents can access the data on a web-application and provide additional information. The gathered information will be used to develop a regional activity-based travel model, and to assess the long term effect of training on eco-driving by analyzing the fuel consumption and simulating the emissions before and after such training.

Abstract

One purpose of ATMS is discovering the bottlenecks and taking some actions to improve global performance of traffic network. However, traffic bottlenecks vary with spatial and temporal environment, which make them not easy to define and discover. A spatiotemporal traffic ...Lead moreOne purpose of ATMS is discovering the bottlenecks and taking some actions to improve global performance of traffic network. However, traffic bottlenecks vary with spatial and temporal environment, which make them not easy to define and discover. A spatiotemporal traffic bottlenecks mining model is proposed in this paper, which utilizes the raw data in location based services and thus has the cost and coverage advantages comparing to the traditional methods. This model is able to discover the STB as well as finds out the time sequence association rule between the congestion areas, which provides useful decision information for ATMS administrators

Abstract

The framework architecture for maritime transport is established by the European MarNIS-project, aiming Pan-European solutions to increase maritime safety, efficiency and protection of the environment. The architecture is established through an iterative improvement proce...Lead moreThe framework architecture for maritime transport is established by the European MarNIS-project, aiming Pan-European solutions to increase maritime safety, efficiency and protection of the environment. The architecture is established through an iterative improvement process starting with the ARKTRANS framework architecture for multimodal transport and the COMPRIS architecture for inland waterways. Through involvement of maritime experts, the architecture is refined to provide a total picture of the maritime sector. By focusing on generic responsibilities, the architecture abstract away from local differences. A reference mode, roles, tasks and processes arrange for definitions of new maritime concepts representing new practices and solutions.

Abstract

This paper presents the specificities of the Japanese tollways and in particular the usage of ETC systems. In order to anticipate the increase of ETC users, future scenario of toll plaza layout (gates type and position) has to be evaluated. Microsimulation tool is used to...Lead moreThis paper presents the specificities of the Japanese tollways and in particular the usage of ETC systems. In order to anticipate the increase of ETC users, future scenario of toll plaza layout (gates type and position) has to be evaluated. Microsimulation tool is used to assess performances and safety aspects. In order to do it properly, a gate selection model is developed, calibrated and implemented.

Abstract

With indefinite noises and nonlinear characteristics, real-time estimating states of the dead reckoning (DR) unit is much more difficult than that of the other measuring sensors, which used in vehicle integrated navigation systems. Compared with the well known extended Ka...Lead moreWith indefinite noises and nonlinear characteristics, real-time estimating states of the dead reckoning (DR) unit is much more difficult than that of the other measuring sensors, which used in vehicle integrated navigation systems. Compared with the well known extended Kalman filter (EKF), a recurrent neural network is proposed for the solution, which not only improves the location precision, the adaptive ability of resisting disturbances, but also avoids calculating the analytic derivation and Jacobian matrices of the nonlinear system model. In order to test the performances of the recurrent neural network, these two methods are used to estimate states of the vehicle DR navigation system. Simulation results show the recurrent neural network is superior to the EKF and is a more ideal filtering method for vehicle DR navigation.

Abstract

In recent years, the probe vehicle system using vehicles equipped with GPS units to collect traffic information has attracted much attention. Travel time can be estimated according to the time and space information collected from this system. The estimation accuracy can b...Lead moreIn recent years, the probe vehicle system using vehicles equipped with GPS units to collect traffic information has attracted much attention. Travel time can be estimated according to the time and space information collected from this system. The estimation accuracy can be increased by compiling statistics on the long-term data accumulation. However, the statistical data can not reflect non-recurrent traffic congestion caused by traffic accidents or road construction. On the other hand, the existing traffic information collecting system in Japan, VICS provides real time traffic regulation information with traffic accidents or road construction. This study provides a data fusion algorithm to combine the real time traffic regulation provided by VICS with travel time information obtained from the probe vehicle system. It is then applied to a case study in Nagoya City, and the result shows that the accuracy of estimation can be increased by about 6%.

Abstract

This paper explores a microscopic traffic model (a Kinematic Car-following model at Signalized intersections: a KCS traffic model) based on one-dimensional kematic equations in physics. The formulae are derived for two different vehicle groups: a trajectory equation for t...Lead moreThis paper explores a microscopic traffic model (a Kinematic Car-following model at Signalized intersections: a KCS traffic model) based on one-dimensional kematic equations in physics. The formulae are derived for two different vehicle groups: a trajectory equation for the leading vehicle and a trajectory equation for the following vehicles. Hence, in each time-step, the KCS traffic model can represent detailed motion of vehicles from the detector to the stop-line, and can provide plenty of information between them. A comparative evaluation in sensitivity of delay with respect to the variations in the start of green time between the proposed KCS traffic model and the previously known linear model (the Vertical queueing model) is discussed.

Abstract

Despite the fact that manual optimisation approaches represent good engineering practise, their performance is restricted due to complexity of the problem. But also numerical methods suffer from complexity of the NP-hard optimisation problem which is discrete in time and ...Lead moreDespite the fact that manual optimisation approaches represent good engineering practise, their performance is restricted due to complexity of the problem. But also numerical methods suffer from complexity of the NP-hard optimisation problem which is discrete in time and space. Therefore, this study presents a new offset optimisation method employing the Cell Transmission Model, which is a 1st order discrete traffic flow model The proposed method further particularly cares about optimisation strategies and the respective running time requirements. In this context an optimisation algorithm based on Genetic Algorithm is developed, which uses a decomposition of the problem.

Abstract

By identifying the abnormity in the dynamic traffic data and getting rid of and supplement, the fault data is repaired. it is proved that the method in this paper can improve the reliability of the input of transport model. And it is applicable and keep the quality of the...Lead moreBy identifying the abnormity in the dynamic traffic data and getting rid of and supplement, the fault data is repaired. it is proved that the method in this paper can improve the reliability of the input of transport model. And it is applicable and keep the quality of the fundamental data for dynamic traffic data analysis.

Abstract

This study analyzes the effect of road pricing by the model which has the following characteristics. 1) The model integrates trip generation (i.e. activity choice), destination choice, mode choice and route choice. 2) The model considers hourly variation of traffic condit...Lead moreThis study analyzes the effect of road pricing by the model which has the following characteristics. 1) The model integrates trip generation (i.e. activity choice), destination choice, mode choice and route choice. 2) The model considers hourly variation of traffic condition including queue evolution. 3) Trip chain along the time axis can be reproduced approximately. The evaluation of road pricing in Nagoya Metropolitan Area shows that the environment situation is effectively improved due to the reduction of car trips, but visitors are decreased greatly because of the small shift to railway and the change of destination.

Abstract

This paper outlines four different ways of reducing pollution from road transport: Incentives for improving the load factor in inner-city freight distribution. Trucks with a load factor of at least 65 per cent are allowed to use lanes normally reserved for public transpor...Lead moreThis paper outlines four different ways of reducing pollution from road transport: Incentives for improving the load factor in inner-city freight distribution. Trucks with a load factor of at least 65 per cent are allowed to use lanes normally reserved for public transport, giving an incentive to use trucks more efficiently. Incentives for car sharing. Cars owned by the city are let to use by car poolers on evenings and week-ends, thus decreasing the total number of cars needed. Restricted Environmental Zone. In the inner city, only trucks that adhere to strict pollution standards are allowed, with a strong incentive for haulers to use the least polluting technology available. Incentive Scheme for Eco Vehicles. Free parking for “green cars“ is a major contributor to Goteborg’s status as Sweden’s “number one green car city”. These urban traffic management tools have worked well in Goteborg and can be used in other cities worldwide, smaller as well as larger.

Abstract

Traffic sign detection is one of the important tasks for a driver assistance system. This paper describes a shape-based method for traffic sign detection. Multiple shapes including circles, regular and non-regular polygons can be detected under a general framework. The no...Lead moreTraffic sign detection is one of the important tasks for a driver assistance system. This paper describes a shape-based method for traffic sign detection. Multiple shapes including circles, regular and non-regular polygons can be detected under a general framework. The novelty of our approach is that different shapes can be simultaneously located and classified. It is implemented through taking account of both voting accumulations and voting directions. We show that the approach can reduce false detection and computation burden compared to some existing methods. Moreover, by modeling a shape based on its partial radial symmetry characteristics and the geometrical relationship among the symmetry centers, our approach is extended to detect non-regular polygons. Experiments on traffic sign detection demonstrate good performance of our method.

Abstract

This paper presents a method of moving vehicles detection for driving-assistant system. Monocular camera is used because of the shorter processing time. An object candidates sifting method based on the classification of image pixels is used to narrow down the processing a...Lead moreThis paper presents a method of moving vehicles detection for driving-assistant system. Monocular camera is used because of the shorter processing time. An object candidates sifting method based on the classification of image pixels is used to narrow down the processing areas. Then we proposed a fast feature points extraction and matching method using the edge information. We detect the objects by velocity vectors grouping, and projection geometry is used to calculate the relative position of the objects. Finally, the experiments are carried out to prove the algorithm is fast and effective.

Abstract

We present an approach to managing vehicle network resources for diverse data traffic types, such as safety, traffic, and commercial. Our approach uses application-specific utility descriptions, which are reduced to simpler and more compact ``microutility'' approximations...Lead moreWe present an approach to managing vehicle network resources for diverse data traffic types, such as safety, traffic, and commercial. Our approach uses application-specific utility descriptions, which are reduced to simpler and more compact ``microutility'' approximations. These microutilities travel with the data to guide critical in-transit resource decisions such as dropping data, access to infrastructure networks, and storing data for later forwarding. Our system dynamically adjusts the quality of service in the network to support diverse application needs efficiently and fairly. This paper describes the system, the algorithms used, and presents the results of several simulation studies.

Abstract

To capture the complex nature of intersection queue dynamics, this research proposed a recursive nonparametric regression model and implemented it to forecast traffic flows and queue evolution in a congested actuated intersection. The major contribution of this study is t...Lead moreTo capture the complex nature of intersection queue dynamics, this research proposed a recursive nonparametric regression model and implemented it to forecast traffic flows and queue evolution in a congested actuated intersection. The major contribution of this study is that the proposed model can be used to substitute traditional simulation software in the lower level of a real time traffic control system to search the optimal control variables, and then utilize the found solutions as the inputs in the simulation software in the upper level of that control system to attain the system performances. In this way, the advantages of traditional mathematical modeling approach and simulation software could be both utilized, while their disadvantages could be effectively avoided. The proposed model also takes the external un-quantifiable or non-easily quantifiable factors influence on the traffic pattern into consideration.

Abstract

The TJATCMS prototype is a real-time traffic-adaptive signal control strategy that is suitable for management and control of traffic conditions in Chinese cities. In this paper we firstly describe three layers in TJATCMS (network layer, group layer, and intersection layer...Lead moreThe TJATCMS prototype is a real-time traffic-adaptive signal control strategy that is suitable for management and control of traffic conditions in Chinese cities. In this paper we firstly describe three layers in TJATCMS (network layer, group layer, and intersection layer), and its normal strategy and special strategy, secondly present the model architecture including three major parts. Then, the software including four modules (network flow module, group module, isolated intersection module, traffic flow simulation module, and TJATCMS database) is introduced. At last, we present some simulation and field experiment results.

Abstract

ITS market package screening is one of the fundamental tasks in ITS planning. Recognizing that the state-of-the-art still falls short of developing a local ITS market package plan in a systematic manner, this paper presents a Multi-Attribute Utility Theory (MAUT) approach...Lead moreITS market package screening is one of the fundamental tasks in ITS planning. Recognizing that the state-of-the-art still falls short of developing a local ITS market package plan in a systematic manner, this paper presents a Multi-Attribute Utility Theory (MAUT) approach to address this problem. The MAUT model was carefully constructed based on ITS planning objectives and available data resources. With the calculation of aggregated utilities, the market packages were ranked so decision makers can make rational choices accordingly. Sensitivity analysis was conducted to examine how changes in performance measure weights would affect the final ranking results. Compared to the conventional market package screening method, the MAUT approach provides decision makers more detailed information and data in order to better understand which ITS strategies are more suitable to address the local transportation problems and user needs.

Abstract

In this study, vehicle behaviors during signal change intervals at signalized intersections are analyzed and the characteristics of unreasonable vehicle behavior during these intervals are identified. Based on the analysis, accident probabilities in an intersection are es...Lead moreIn this study, vehicle behaviors during signal change intervals at signalized intersections are analyzed and the characteristics of unreasonable vehicle behavior during these intervals are identified. Based on the analysis, accident probabilities in an intersection are estimated without taking into account possible avoidance maneuvers carried out by drivers. This study clarifies the danger caused by unreasonable vehicle behavior and makes it possible to evaluate the danger at signal change intervals in signalized intersections quantitatively.

Abstract

This paper presents an off-line traffic sign detection approach, whose core is based on the combination with the color feature of traffic signs, shape feature and degree of circularity. Matlab-Image-processing toolbox is used for this purpose. In order to reduce the compu...Lead moreThis paper presents an off-line traffic sign detection approach, whose core is based on the combination with the color feature of traffic signs, shape feature and degree of circularity. Matlab-Image-processing toolbox is used for this purpose. In order to reduce the computational cost, a pre-processing of the image is applied before the core. Then, we employ the obvious redness and whiteness attribute of traffic signs to coarsely eliminate the non-redness and non-whiteness pixels in the input image. Again, a shape segment approach based on fractal dimension method is applied to extract regular shape. Finally, Degree of circularity is used to verdict the traffic signs. Experimental results show that our proposed method offers satisfactory performance.