Pub Date : 2004-06-14DOI: 10.1109/IVS.2004.1336474
N. Zorka, K. Cheok
Predictive sensing applications are starting to find wide applications in automotive safety applications. In collision situations the need to alert the driver and to take effective countermeasures to meet the needs of the vehicle occupant safety is becoming increasingly more dependent on sensors. Electronic systems to provide warning and to implement active adaptation of occupant restraints to provide for enhanced safety protection are becoming more dependent on active safety sensors. This paper deals with a system that uses radar sensors that provides the ability to cluster the number of vehicles based on radar return signals and to actively track their movement with a Kalman filter.
{"title":"Dynamic cluster tracking technique for traffic monitoring using on-vehicle radar","authors":"N. Zorka, K. Cheok","doi":"10.1109/IVS.2004.1336474","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336474","url":null,"abstract":"Predictive sensing applications are starting to find wide applications in automotive safety applications. In collision situations the need to alert the driver and to take effective countermeasures to meet the needs of the vehicle occupant safety is becoming increasingly more dependent on sensors. Electronic systems to provide warning and to implement active adaptation of occupant restraints to provide for enhanced safety protection are becoming more dependent on active safety sensors. This paper deals with a system that uses radar sensors that provides the ability to cluster the number of vehicles based on radar return signals and to actively track their movement with a Kalman filter.","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":"116633847","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.2004.1336378
R. Boel, L. Mihaylova
Traffic flow on freeways is a nonlinear, many-particle phenomenon, with complex interactions between the vehicles. This paper presents a stochastic hybrid model of freeway traffic at a time scale and at a level of detail suitable for on-line flow estimation, for routing and ramp metering control. The model describes the evolution of continuous and discrete state variables. The freeway is considered as a network of components, each component representing a different section of the network. The traffic model, designed from physical considerations, comprises sending and receiving functions describing the downstream and upstream propagation of perturbations to be controlled. Results from simulation investigations illustrate the effectiveness of our model compared to the well-known METANET model.
{"title":"Modelling freeway networks by hybrid stochastic models","authors":"R. Boel, L. Mihaylova","doi":"10.1109/IVS.2004.1336378","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336378","url":null,"abstract":"Traffic flow on freeways is a nonlinear, many-particle phenomenon, with complex interactions between the vehicles. This paper presents a stochastic hybrid model of freeway traffic at a time scale and at a level of detail suitable for on-line flow estimation, for routing and ramp metering control. The model describes the evolution of continuous and discrete state variables. The freeway is considered as a network of components, each component representing a different section of the network. The traffic model, designed from physical considerations, comprises sending and receiving functions describing the downstream and upstream propagation of perturbations to be controlled. Results from simulation investigations illustrate the effectiveness of our model compared to the well-known METANET model.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"4 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":"121821215","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.2004.1336422
G. Hegeman
This paper shows results of an observation of overtaking frequencies on roads with opposing traffic. This observation is a first step of research regarding potential safety effects of advanced driver assistance systems on overtaking on two lane rural roads. We determine overtaking frequencies as a function of flow rates on both directions, distinguishing different vehicle types. Observed overtaking frequencies are lower than overtaking demand, especially when the directional split becomes more equal. Therefore we recommend adding directional split to the equation to calculate overtaking frequency.
{"title":"Overtaking frequency and advanced driver assistance systems","authors":"G. Hegeman","doi":"10.1109/IVS.2004.1336422","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336422","url":null,"abstract":"This paper shows results of an observation of overtaking frequencies on roads with opposing traffic. This observation is a first step of research regarding potential safety effects of advanced driver assistance systems on overtaking on two lane rural roads. We determine overtaking frequencies as a function of flow rates on both directions, distinguishing different vehicle types. Observed overtaking frequencies are lower than overtaking demand, especially when the directional split becomes more equal. Therefore we recommend adding directional split to the equation to calculate overtaking frequency.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"24 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":"125246498","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.2004.1336475
R. Mobus, U. Kolbe
This paper presents algorithms and techniques for single-sensor tracking and multi-sensor fusion of infrared and radar data. The results show that fusing radar data with infrared data considerably increases detection range, reliability and accuracy of the object tracking. This is mandatory for further development of driver assistance systems. Using multiple model filtering for sensor fusion applications helps to capture the dynamics of maneuvering objects while still achieving smooth object tracking for not maneuvering objects. This is important when safety and comfort systems have to make use of the same sensor information. Comfort systems generally require smoothly filtered data whereas for safety systems it is crucial to capture maneuvers of other road users as fast as possible. Multiple model filtering and probabilistic data association techniques are presented and all presented algorithms are tested in real-time on standard PC systems.
{"title":"Multi-target multi-object tracking, sensor fusion of radar and infrared","authors":"R. Mobus, U. Kolbe","doi":"10.1109/IVS.2004.1336475","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336475","url":null,"abstract":"This paper presents algorithms and techniques for single-sensor tracking and multi-sensor fusion of infrared and radar data. The results show that fusing radar data with infrared data considerably increases detection range, reliability and accuracy of the object tracking. This is mandatory for further development of driver assistance systems. Using multiple model filtering for sensor fusion applications helps to capture the dynamics of maneuvering objects while still achieving smooth object tracking for not maneuvering objects. This is important when safety and comfort systems have to make use of the same sensor information. Comfort systems generally require smoothly filtered data whereas for safety systems it is crucial to capture maneuvers of other road users as fast as possible. Multiple model filtering and probabilistic data association techniques are presented and all presented algorithms are tested in real-time on standard PC systems.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"65 2 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":"126986177","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.2004.1336511
K. Weiß, N. Kaempchen, A. Kirchner
Volkswagen research has developed a system for vehicle surround perception which integrates different sensor data of the environment into a combined description by using a single model Kalman tracker. This paper deals with the extension of the tracking system by means of an interacting multiple-model algorithm (IMM) to improve the tracking stability during curves and to detect lane changes of the observed target vehicle. The applied IMM-tracker uses specialized models for lateral and longitudinal motion that are partly affected by curvature estimation. The technique is tested with recorded sequences of measurement data and shows robust tracking and well-fitting classification of the dynamical behavior of the targets.
{"title":"Multiple-model tracking for the detection of lane change maneuvers","authors":"K. Weiß, N. Kaempchen, A. Kirchner","doi":"10.1109/IVS.2004.1336511","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336511","url":null,"abstract":"Volkswagen research has developed a system for vehicle surround perception which integrates different sensor data of the environment into a combined description by using a single model Kalman tracker. This paper deals with the extension of the tracking system by means of an interacting multiple-model algorithm (IMM) to improve the tracking stability during curves and to detect lane changes of the observed target vehicle. The applied IMM-tracker uses specialized models for lateral and longitudinal motion that are partly affected by curvature estimation. The technique is tested with recorded sequences of measurement data and shows robust tracking and well-fitting classification of the dynamical behavior of the targets.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"82 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":"134192701","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.2004.1336482
U. Scheunert, H. Cramer, Gerd Wanielik
This article presents a multi sensor approach for driver assistance systems: the detection and tracking of pedestrians in a road environment. A multi sensor system consisting of a far infrared camera and a laser scanning device is used for the detection and precise localization of pedestrians. Kalman filter based data fusion handles the combination of the sensor information of the infrared camera and of the laser scanner. Arranging a set of Kalman filters in parallel, a multi sensor/multi target tracking system was created. The usage of suitable movement models has a great influence on the performance of the tracking system. Several types of models are discussed focussing on the typical behavior of pedestrians in road environments. The multi sensor/multi target tracking system is installed on a test vehicle to obtain practical results which is discussed in this article too.
{"title":"Multi sensor based tracking of pedestrians: a survey of suitable movement models","authors":"U. Scheunert, H. Cramer, Gerd Wanielik","doi":"10.1109/IVS.2004.1336482","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336482","url":null,"abstract":"This article presents a multi sensor approach for driver assistance systems: the detection and tracking of pedestrians in a road environment. A multi sensor system consisting of a far infrared camera and a laser scanning device is used for the detection and precise localization of pedestrians. Kalman filter based data fusion handles the combination of the sensor information of the infrared camera and of the laser scanner. Arranging a set of Kalman filters in parallel, a multi sensor/multi target tracking system was created. The usage of suitable movement models has a great influence on the performance of the tracking system. Several types of models are discussed focussing on the typical behavior of pedestrians in road environments. The multi sensor/multi target tracking system is installed on a test vehicle to obtain practical results which is discussed in this article too.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"123 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":"134424900","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.2004.1336484
M. Bertozzi, A. Broggi, P. Grisleri, A. Tibaldi, Michael Rose
This paper describes a system for evaluating pedestrian detection algorithm results. The developed tool allows a human operator to annotate on a file all pedestrians in a previously acquired video sequence. A similar file is produced by the algorithm being tested using the same annotation engine. A matching rule has been established to validate the association between items of the two files. For each frame a statistical analyzer extracts the number of mis-detections, both positive and negative, and correct detections. Using these data, statistics about the algorithm behavior are computed with the aim of tuning parameters and pointing out recognition weaknesses in particular situations.
{"title":"A tool for vision based pedestrian detection performance evaluation","authors":"M. Bertozzi, A. Broggi, P. Grisleri, A. Tibaldi, Michael Rose","doi":"10.1109/IVS.2004.1336484","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336484","url":null,"abstract":"This paper describes a system for evaluating pedestrian detection algorithm results. The developed tool allows a human operator to annotate on a file all pedestrians in a previously acquired video sequence. A similar file is produced by the algorithm being tested using the same annotation engine. A matching rule has been established to validate the association between items of the two files. For each frame a statistical analyzer extracts the number of mis-detections, both positive and negative, and correct detections. Using these data, statistics about the algorithm behavior are computed with the aim of tuning parameters and pointing out recognition weaknesses in particular situations.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"85 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":"133383193","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.2004.1336514
C. Maihofer, R. Eberhardt
Geocast in vehicular ad hoc networks allows to realize applications like virtual warning signs for improved road safety, which address a geographical area rather than an individual vehicle. In this paper we propose to include caching in the geocast forwarding scheme and improved neighborhood selection to address in particular the high velocities of vehicles. High velocities of vehicular networks are a major difference to usual mobile ad hoc networks which assume only moderate node movement. We show that a cache for presently unforwardable messages caused by network partitioning or unfavorable neighbors can significantly improve the geocast delivery success ratio. The improved neighborhood selection taking frequent neighborhood changes into account significantly decreases network load and decreased end-to-end delivery delay.
{"title":"Geocast in vehicular environments: caching and transmission range control for improved efficiency","authors":"C. Maihofer, R. Eberhardt","doi":"10.1109/IVS.2004.1336514","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336514","url":null,"abstract":"Geocast in vehicular ad hoc networks allows to realize applications like virtual warning signs for improved road safety, which address a geographical area rather than an individual vehicle. In this paper we propose to include caching in the geocast forwarding scheme and improved neighborhood selection to address in particular the high velocities of vehicles. High velocities of vehicular networks are a major difference to usual mobile ad hoc networks which assume only moderate node movement. We show that a cache for presently unforwardable messages caused by network partitioning or unfavorable neighbors can significantly improve the geocast delivery success ratio. The improved neighborhood selection taking frequent neighborhood changes into account significantly decreases network load and decreased end-to-end delivery delay.","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":"133821434","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.2004.1336447
J. M. Collado, C. Hilario, A. de la Escalera, J. M. Armingol
One of the Advanced Driver Assistance Systems are being researched nowadays for Intelligent Vehicles has to deal -with the detection and tracking of other vehicles. It will have many applications: Platooning, Stop&go, Blind angle perception, Manoeuvres supervisor. In this paper, a system based on computer vision is presented. A geometric model of the vehicle is defined where its energy function includes information of the shape and symmetry of the vehicle and the shadow it produces. A genetic algorithm finds the optimum parameter values. Examples of real images are shown to validate the algorithm.
{"title":"Model based vehicle detection for intelligent vehicles","authors":"J. M. Collado, C. Hilario, A. de la Escalera, J. M. Armingol","doi":"10.1109/IVS.2004.1336447","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336447","url":null,"abstract":"One of the Advanced Driver Assistance Systems are being researched nowadays for Intelligent Vehicles has to deal -with the detection and tracking of other vehicles. It will have many applications: Platooning, Stop&go, Blind angle perception, Manoeuvres supervisor. In this paper, a system based on computer vision is presented. A geometric model of the vehicle is defined where its energy function includes information of the shape and symmetry of the vehicle and the shadow it produces. A genetic algorithm finds the optimum parameter values. Examples of real images are shown to validate the algorithm.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"63 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":"115044748","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.2004.1336391
J. Kolodko, L. Vlacic
We introduce a motion estimation algorithm that fuses visual and range data to give an unambiguous estimate of the velocity of objects visible to a camera and range sensor. Dynamic scale space is used to avoid temporal aliasing and a novel robust estimator based on Least Trimmed Squares is used to smooth results between boundaries established using range data. Simulation results (from a specially developed simulation environment) and experimental results (from an FPGA based implementation of our algorithm) show that our approach gives accurate motion estimates.
{"title":"Fusion of range and vision for real-time motion estimation","authors":"J. Kolodko, L. Vlacic","doi":"10.1109/IVS.2004.1336391","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336391","url":null,"abstract":"We introduce a motion estimation algorithm that fuses visual and range data to give an unambiguous estimate of the velocity of objects visible to a camera and range sensor. Dynamic scale space is used to avoid temporal aliasing and a novel robust estimator based on Least Trimmed Squares is used to smooth results between boundaries established using range data. Simulation results (from a specially developed simulation environment) and experimental results (from an FPGA based implementation of our algorithm) show that our approach gives accurate motion estimates.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"81 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":"114458750","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：