Pub Date : 2004-06-14DOI: 10.1109/IVS.2004.1336377
A. Peripimeno, D. Anguita, P. Chiappini
In this paper we focus on bus fleets and propose an application of artificial intelligence (transductive inference for function estimation) which utilizes data from the vehicle tracking system in order to enforce the schedule monitoring of the bus and thus providing more accurate information for decision making activities. This is achieved by estimating the time of arrivals and departures of the buses at certain points of the journey (main bus stops, interchange points, crossroads) which are crucial for the management of the fleet.
{"title":"Smart data re-sampling for bus fleet management","authors":"A. Peripimeno, D. Anguita, P. Chiappini","doi":"10.1109/IVS.2004.1336377","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336377","url":null,"abstract":"In this paper we focus on bus fleets and propose an application of artificial intelligence (transductive inference for function estimation) which utilizes data from the vehicle tracking system in order to enforce the schedule monitoring of the bus and thus providing more accurate information for decision making activities. This is achieved by estimating the time of arrivals and departures of the buses at certain points of the journey (main bus stops, interchange points, crossroads) which are crucial for the management of the fleet.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126170868","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336367
A. Pellecchia, J. Hedelbrunner
The main goal of this work is to develop a system capable of imitating the mechanisms by which specific events, taking place in the traffic scenario, trigger driver decisions. Specifically the process that leads to start an overtaking maneuver is addressed. The core of this paper regards the problem of the representation in a compact and meaningful form of the driving environment, the way of interpreting such a representation, that of understanding which events trigger a decision in a driver and the related issue of learning typical driving styles in an artificial behavioral system. The method followed has been primarily inspired by the research on Dynamical Systems for Behavior Generation, whereas the basic criteria for behavior analysis have been derived from measurements on real drivers.
{"title":"Modeling real driving behaviors through attractor dynamics for motivation","authors":"A. Pellecchia, J. Hedelbrunner","doi":"10.1109/IVS.2004.1336367","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336367","url":null,"abstract":"The main goal of this work is to develop a system capable of imitating the mechanisms by which specific events, taking place in the traffic scenario, trigger driver decisions. Specifically the process that leads to start an overtaking maneuver is addressed. The core of this paper regards the problem of the representation in a compact and meaningful form of the driving environment, the way of interpreting such a representation, that of understanding which events trigger a decision in a driver and the related issue of learning typical driving styles in an artificial behavioral system. The method followed has been primarily inspired by the research on Dynamical Systems for Behavior Generation, whereas the basic criteria for behavior analysis have been derived from measurements on real drivers.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127721593","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336402
H. Sunyoto, W. V. D. Mark, D. Gavrila
With recent hardware advances, real-time dense stereo vision becomes increasingly feasible for general-purpose processors. This has important benefits for the intelligent vehicles domain, alleviating object segmentation problems when sensing complex, cluttered traffic scenes. In this paper, we presents a framework of real-time dense stereo vision algorithms that all based on a SIMD architecture. We distinguish different methodical components and examine their performance-speed trade-off. We furthermore compare the resulting algorithmic variations with an existing public source dynamic programming implementation from OpenCV and with the stereo methods discussed in Sharstein and Szeliski's survey. Unlike the previous, we evaluate all stereo vision algorithms using realistically looking simulated data as well as real data, from complex urban traffic scenes.
{"title":"A comparative study of fast dense stereo vision algorithms","authors":"H. Sunyoto, W. V. D. Mark, D. Gavrila","doi":"10.1109/IVS.2004.1336402","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336402","url":null,"abstract":"With recent hardware advances, real-time dense stereo vision becomes increasingly feasible for general-purpose processors. This has important benefits for the intelligent vehicles domain, alleviating object segmentation problems when sensing complex, cluttered traffic scenes. In this paper, we presents a framework of real-time dense stereo vision algorithms that all based on a SIMD architecture. We distinguish different methodical components and examine their performance-speed trade-off. We furthermore compare the resulting algorithmic variations with an existing public source dynamic programming implementation from OpenCV and with the stereo methods discussed in Sharstein and Szeliski's survey. Unlike the previous, we evaluate all stereo vision algorithms using realistically looking simulated data as well as real data, from complex urban traffic scenes.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126699091","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336426
Marco A. Wiering, J. Vreeken, J. V. Veenen, A. Koopman
Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red and green lights at each intersection, and sets the traffic lights to green for the configuration maximizing individual car gains. For testing our adaptive traffic light controllers, we developed the green light district simulator. The experimental results show that the adaptive algorithms can strongly reduce average waiting times of cars compared to three hand-designed controllers.
{"title":"Simulation and optimization of traffic in a city","authors":"Marco A. Wiering, J. Vreeken, J. V. Veenen, A. Koopman","doi":"10.1109/IVS.2004.1336426","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336426","url":null,"abstract":"Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red and green lights at each intersection, and sets the traffic lights to green for the configuration maximizing individual car gains. For testing our adaptive traffic light controllers, we developed the green light district simulator. The experimental results show that the adaptive algorithms can strongly reduce average waiting times of cars compared to three hand-designed controllers.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127112766","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336349
G. Grubb, A. Zelinsky, L. Nilsson, M. Rilbe
Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive pedestrian protection systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5% and 0.4%, respectively.
{"title":"3D vision sensing for improved pedestrian safety","authors":"G. Grubb, A. Zelinsky, L. Nilsson, M. Rilbe","doi":"10.1109/IVS.2004.1336349","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336349","url":null,"abstract":"Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive pedestrian protection systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5% and 0.4%, respectively.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126567258","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336380
L. Vanajakshi, L. Rilett
The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems in transportation networks, is vital to the intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the contest of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.
{"title":"A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed","authors":"L. Vanajakshi, L. Rilett","doi":"10.1109/IVS.2004.1336380","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336380","url":null,"abstract":"The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems in transportation networks, is vital to the intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the contest of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123486314","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336390
N. Kawasaki, U. Kiencke
In this paper, a new architecture for sensor fusion for advanced driver assistant system (ADAS) is proposed. This architecture is based on Bayesian Network and plays the role of a platform for integrating various sensors such as Lidar, Radar and Vision sensors into sensor fusion systems. This architecture has the following 3 major advantages: (1) It makes structure and signal flow of the complicated fusion systems easy to understand (2) It increases the reusability of the sensor algorithm modules (3) It achieves easy integration of various sensors with different specifications. These advantages are confirmed by vehicle test.
{"title":"Standard platform for sensor fusion on advanced driver assistance system using Bayesian Network","authors":"N. Kawasaki, U. Kiencke","doi":"10.1109/IVS.2004.1336390","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336390","url":null,"abstract":"In this paper, a new architecture for sensor fusion for advanced driver assistant system (ADAS) is proposed. This architecture is based on Bayesian Network and plays the role of a platform for integrating various sensors such as Lidar, Radar and Vision sensors into sensor fusion systems. This architecture has the following 3 major advantages: (1) It makes structure and signal flow of the complicated fusion systems easy to understand (2) It increases the reusability of the sensor algorithm modules (3) It achieves easy integration of various sensors with different specifications. These advantages are confirmed by vehicle test.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123710115","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336442
M. Krips, J. Velten, A. Kummert, A. Teuner
Road traffic hazards typically occur on motorways during lane change, if another vehicle besides the own one has been overlooked. This can happen easily, if the other vehicle is in the blind spot and the driver has not assured accurately that there is no other vehicle alongside. In this paper, a tracking method for vehicles approaching from the rear is described. They are classified as potential targets by means of a shadow based classification algorithm.
{"title":"AdTM tracking for blind spot collision avoidance","authors":"M. Krips, J. Velten, A. Kummert, A. Teuner","doi":"10.1109/IVS.2004.1336442","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336442","url":null,"abstract":"Road traffic hazards typically occur on motorways during lane change, if another vehicle besides the own one has been overlooked. This can happen easily, if the other vehicle is in the blind spot and the driver has not assured accurately that there is no other vehicle alongside. In this paper, a tracking method for vehicles approaching from the rear is described. They are classified as potential targets by means of a shadow based classification algorithm.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122753111","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336464
J.J. Garcia, A. Hernández, J. Ureña, J.C. Garcia, M. Mazo, J. Lázaro, M.C. Perez, F. Álvarez
In this work an intelligent infrastructure is shown, which allows to detect obstacles in railways, based on optical emitters. The sensorial system is based on a barrier of emitters and another of receivers, placed each one of them at one side of the railway. Apart from the disposition of the sensorial system, is also presented a codification method of the emission in order to detect the reception or the non-reception of transmissions between an emitter and a receiver. The presented method is based on a signal codification using complementary sequence pairs, suitably adapted for their simultaneous emission through the transmission channel. A high reliability under adverse conditions is achieved with the developed system, being possible to detect the presence of obstacles, and to inform about their situation.
{"title":"Low cost obstacle detection for smart railway infrastructures","authors":"J.J. Garcia, A. Hernández, J. Ureña, J.C. Garcia, M. Mazo, J. Lázaro, M.C. Perez, F. Álvarez","doi":"10.1109/IVS.2004.1336464","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336464","url":null,"abstract":"In this work an intelligent infrastructure is shown, which allows to detect obstacles in railways, based on optical emitters. The sensorial system is based on a barrier of emitters and another of receivers, placed each one of them at one side of the railway. Apart from the disposition of the sensorial system, is also presented a codification method of the emission in order to detect the reception or the non-reception of transmissions between an emitter and a receiver. The presented method is based on a signal codification using complementary sequence pairs, suitably adapted for their simultaneous emission through the transmission channel. A high reliability under adverse conditions is achieved with the developed system, being possible to detect the presence of obstacles, and to inform about their situation.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121793266","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 : 2004-06-14DOI: 10.1109/IVS.2004.1336405
M. Basset, C. Cudel, V. Georges, S. Mouhoub, J. Baujon
Recent studies on driver behaviour have shown that perception - mainly visual but also proprioceptive perception plays a key role in the "driver-vehicle-road" system and so considerably affects the driver's decision making. The framework of research work presented here is the behaviour analysis and studies low-cost system (BASIL) based on the real time visual analysis tool called EyeAccessPilot (EAP) system. This system, dedicated to driver's behaviour analysis, collects synchronously all the available embedded information: the visual perception via 2D eye's direction, the trajectory followed, accelerations... In this framework, a new development is presented here in order to allow the analysis of focusing area of a driver in driving situations, via the automatic detection of Regions of Interest. This post-processing tool considers video sequence acquired with the EyeAcessPilot system. As the displacement of the head is effective during driving phase and is not measured, the aim of this work is to track automatically defined Regions Of Interest (ROI) all along the stored video sequence. This automatic tracker is based on detection of singular points in images.
{"title":"Automatic region of interest tracking for visual characterization of the driver's behaviour","authors":"M. Basset, C. Cudel, V. Georges, S. Mouhoub, J. Baujon","doi":"10.1109/IVS.2004.1336405","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336405","url":null,"abstract":"Recent studies on driver behaviour have shown that perception - mainly visual but also proprioceptive perception plays a key role in the \"driver-vehicle-road\" system and so considerably affects the driver's decision making. The framework of research work presented here is the behaviour analysis and studies low-cost system (BASIL) based on the real time visual analysis tool called EyeAccessPilot (EAP) system. This system, dedicated to driver's behaviour analysis, collects synchronously all the available embedded information: the visual perception via 2D eye's direction, the trajectory followed, accelerations... In this framework, a new development is presented here in order to allow the analysis of focusing area of a driver in driving situations, via the automatic detection of Regions of Interest. This post-processing tool considers video sequence acquired with the EyeAcessPilot system. As the displacement of the head is effective during driving phase and is not measured, the aim of this work is to track automatically defined Regions Of Interest (ROI) all along the stored video sequence. This automatic tracker is based on detection of singular points in images.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"33 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131479595","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：