Pub Date : 2004-06-14DOI: 10.1109/IVS.2004.1336438
M. Moretti, M. Triglia, G. Maffei
Monitoring the different equipments distributed continuously on the railway network and use of diagnostic systems installed in railway vehicles that carry the monitoring function during their runs are important. This paper describes the first European diagnostic train ARCHIMEDE, its configuration, its measuring system and their related technologies as well as the management of the train. Moreover, it depicts how the huge amount of data are managed within the asset management system SIM (Maintenance Information System) of the Italian Railways. The processes described reflect a modern approach to the railway infrastructure management. The most important benefit of ARCHIMEDE is the integration of many parameters and the subsequent correlation of different aspects.
{"title":"ARCHIMEDE - the first European diagnostic train for global monitoring of railway infrastructure","authors":"M. Moretti, M. Triglia, G. Maffei","doi":"10.1109/IVS.2004.1336438","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336438","url":null,"abstract":"Monitoring the different equipments distributed continuously on the railway network and use of diagnostic systems installed in railway vehicles that carry the monitoring function during their runs are important. This paper describes the first European diagnostic train ARCHIMEDE, its configuration, its measuring system and their related technologies as well as the management of the train. Moreover, it depicts how the huge amount of data are managed within the asset management system SIM (Maintenance Information System) of the Italian Railways. The processes described reflect a modern approach to the railway infrastructure management. The most important benefit of ARCHIMEDE is the integration of many parameters and the subsequent correlation of different aspects.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"1 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":"131385530","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.2004.1336360
Shinko Y. Cheng, Mohan M. Trivedi
This paper examines the feasibility of a multi-camera voxel based occupant posture estimation system. Several new considerations are made to allow this tested human body modeling system to work reliably in the passenger seat of a vehicle, including camera position, segmentation, and body modeling with voxel reconstructions all from a constrained 4 camera setup. To describe occupant posture, a partial human body model consisting of a head and torso is proposed. The accuracy of the estimation of this model is compared against ground-truth.
{"title":"Human posture estimation using voxel data for \"smart\" airbag systems: issues and framework","authors":"Shinko Y. Cheng, Mohan M. Trivedi","doi":"10.1109/IVS.2004.1336360","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336360","url":null,"abstract":"This paper examines the feasibility of a multi-camera voxel based occupant posture estimation system. Several new considerations are made to allow this tested human body modeling system to work reliably in the passenger seat of a vehicle, including camera position, segmentation, and body modeling with voxel reconstructions all from a constrained 4 camera setup. To describe occupant posture, a partial human body model consisting of a head and torso is proposed. The accuracy of the estimation of this model is compared against ground-truth.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"79 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":"115069866","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.2004.1336507
O. Gietelink, D. Verburg, K. Labibes, A.F. Oostendorp
This paper presents the tools for design and validation of pre-crash systems: the software tool PRE-crash SCenario ANalyzer (PRESCAN) and the VEhicle-Hardware-In-the-Loop (VEHIL) facility. PRESCAN allows to investigate a pre-crash scenario in simulation. This scenario can then be compared with tests performed in the VEHIL facility for validation of the real sensor and controller of the pre-crash system. Using PRESCAN and VEHIL the development process and more specifically the validation of intelligent vehicles can be carried out safer, cheaper, and more reliable.
本文介绍了用于预碰撞系统设计和验证的工具:预碰撞场景分析仪(PRESCAN)软件工具和车辆-硬件在环(vehicle - hardware - in - loop, vehicle - hardware - in - loop)设施。PRESCAN允许在模拟中调查预崩溃场景。然后，可以将该场景与车辆测试中心进行的测试进行比较，以验证碰撞前系统的真实传感器和控制器。使用PRESCAN和VEHIL，智能汽车的开发过程，更具体地说，验证可以更安全、更便宜、更可靠地进行。
{"title":"Pre-crash system validation with PRESCAN and VEHIL","authors":"O. Gietelink, D. Verburg, K. Labibes, A.F. Oostendorp","doi":"10.1109/IVS.2004.1336507","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336507","url":null,"abstract":"This paper presents the tools for design and validation of pre-crash systems: the software tool PRE-crash SCenario ANalyzer (PRESCAN) and the VEhicle-Hardware-In-the-Loop (VEHIL) facility. PRESCAN allows to investigate a pre-crash scenario in simulation. This scenario can then be compared with tests performed in the VEHIL facility for validation of the real sensor and controller of the pre-crash system. Using PRESCAN and VEHIL the development process and more specifically the validation of intelligent vehicles can be carried out safer, cheaper, and more reliable.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"48 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":"129514158","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.2004.1336489
M. Tons, R. Doerfler, M. Meinecke, M. Obojski
The automotive industry and sensor suppliers have responded to the European Commission's request to reduce the road fatalities by 50% until 2010 and they are developing advanced systems for road safety. Short range radar (SRR) sensors in the 24 GHz domain allow coverage of the surroundings of the vehicle, complementing the existing 77 GHz radars used for adaptive cruise control (ACC) systems since 1999. This paper deals with a special variant of pre-crash systems, namely: "pre-crash for vulnerable road users protection". The target is the protection and collision mitigation of pedestrians and bicyclists versus a vehicle. To achieve trigger information for automatic protection systems (like automatic braking or other reversible systems) as well as warning information for drivers, a high performance sensor platform is necessary. This paper presents approaches from the EC-funded project SAVE-U (sensors and system architecture for vulnerable road users protection) of the fifth framework program of the European Commission. The sensor platform consists of short range radar sensors, cameras in the visible and infrared domain. The focus is located on a high- and low-level- data fusion architecture to fulfill the strong requirements. The intension of this paper is mainly to describe the 24 GHz short range radar sensor development for the detection capability of pedestrians in ranges up to 30 m and the sensor fusion technique.
{"title":"Radar sensors and sensor platform used for pedestrian protection in the EC-funded project SAVE-U","authors":"M. Tons, R. Doerfler, M. Meinecke, M. Obojski","doi":"10.1109/IVS.2004.1336489","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336489","url":null,"abstract":"The automotive industry and sensor suppliers have responded to the European Commission's request to reduce the road fatalities by 50% until 2010 and they are developing advanced systems for road safety. Short range radar (SRR) sensors in the 24 GHz domain allow coverage of the surroundings of the vehicle, complementing the existing 77 GHz radars used for adaptive cruise control (ACC) systems since 1999. This paper deals with a special variant of pre-crash systems, namely: \"pre-crash for vulnerable road users protection\". The target is the protection and collision mitigation of pedestrians and bicyclists versus a vehicle. To achieve trigger information for automatic protection systems (like automatic braking or other reversible systems) as well as warning information for drivers, a high performance sensor platform is necessary. This paper presents approaches from the EC-funded project SAVE-U (sensors and system architecture for vulnerable road users protection) of the fifth framework program of the European Commission. The sensor platform consists of short range radar sensors, cameras in the visible and infrared domain. The focus is located on a high- and low-level- data fusion architecture to fulfill the strong requirements. The intension of this paper is mainly to describe the 24 GHz short range radar sensor development for the detection capability of pedestrians in ranges up to 30 m and the sensor fusion technique.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"6 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":"130292948","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.2004.1336451
Hiroaki Shimizu, T. Poggio
The capability of estimating the walking direction of pedestrian would be useful in many applications such as those involving autonomous vehicles. We introduce an approach for estimating the walking direction of pedestrian from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier. Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance.
{"title":"Direction estimation of pedestrian from multiple still images","authors":"Hiroaki Shimizu, T. Poggio","doi":"10.1109/IVS.2004.1336451","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336451","url":null,"abstract":"The capability of estimating the walking direction of pedestrian would be useful in many applications such as those involving autonomous vehicles. We introduce an approach for estimating the walking direction of pedestrian from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier. Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance.","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":"130870882","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.2004.1336466
J. Roslak, J. Wallaschek
Active lighting systems can contribute towards achieving optimum illumination of the traffic space. These systems can, in a more general way, create the conditions for optimum visual perception by the driver. They aim at achieving homogeneous and intense beam patterns in order to improve driver comfort and safety. They can be considered as first prototypes of a more general class of human centric mechatronic systems which are now introduced in automotive applications. Thanks to the use of new optical concepts for the generation of adaptive beam patterns, effective adjustments of the beam pattern to the traffic situation can be achieved. In this paper, the necessary beam pattern that has to be generated by an individual vehicle is calculated, taking information about the vehicle and its surroundings into account.
{"title":"Active lighting systems for improved road safety","authors":"J. Roslak, J. Wallaschek","doi":"10.1109/IVS.2004.1336466","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336466","url":null,"abstract":"Active lighting systems can contribute towards achieving optimum illumination of the traffic space. These systems can, in a more general way, create the conditions for optimum visual perception by the driver. They aim at achieving homogeneous and intense beam patterns in order to improve driver comfort and safety. They can be considered as first prototypes of a more general class of human centric mechatronic systems which are now introduced in automotive applications. Thanks to the use of new optical concepts for the generation of adaptive beam patterns, effective adjustments of the beam pattern to the traffic situation can be achieved. In this paper, the necessary beam pattern that has to be generated by an individual vehicle is calculated, taking information about the vehicle and its surroundings into account.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"255 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":"132353187","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.2004.1336406
T. Kato, T. Fujii, M. Tanimoto
Various measurement equipments are used for the detection of the driver in a car, such as a CCD camera, an infrared camera, and a depth sensor. The space of the car is narrow so that it limits driver's action. We can expect that the driver can stay in one position in order to capture the image. But captured image can be easily influenced from the environment, such as the outside scene and illumination. The capturing method, which is suitable for detecting person in such environment, needs to be considered. First, we investigated the character of the light wavelength used for capturing. And then we examined the capturing method which is suitable for detecting in a car. Finally we acquired the information of driver with the proposed method and detected the driver's posture by performing image processing.
{"title":"Detection of driver's posture in the car by using far infrared camera","authors":"T. Kato, T. Fujii, M. Tanimoto","doi":"10.1109/IVS.2004.1336406","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336406","url":null,"abstract":"Various measurement equipments are used for the detection of the driver in a car, such as a CCD camera, an infrared camera, and a depth sensor. The space of the car is narrow so that it limits driver's action. We can expect that the driver can stay in one position in order to capture the image. But captured image can be easily influenced from the environment, such as the outside scene and illumination. The capturing method, which is suitable for detecting person in such environment, needs to be considered. First, we investigated the character of the light wavelength used for capturing. And then we examined the capturing method which is suitable for detecting in a car. Finally we acquired the information of driver with the proposed method and detected the driver's posture by performing image processing.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"174 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":"129474024","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.2004.1336376
C. Kelber, W. Webber, G. K. Gomes, M. Lohmann, M. S. Rodrigues, D. Ledur
Drive-by-wire systems have been establishing the technological basis that is opening opportunities for the development of new driver assistance and safety systems, making it possible even for a computer to drive or park a car. Driving a car by using just electronic signals opens also possibilities for the development of new human machine interfaces (H.M.I.) that can eventually substitute the current steering wheel and pedals structure. For some physically handicapped people, however, this signifies the possibility of driving the family's car by just attaching the appropriate H.M.I. on it, which could be, for example, a joystick. In this article the use of a joystick as H.M.I, and its relation to the vehicle dynamics is analyzed, and to overcome possible "fishtailing movements" an active steering unit with integrated ACC feature, incorporated to the joystick, is proposed.
{"title":"Active steering unit with integrated ACC for X-by-wire vehicles using a joystick as H.M.I","authors":"C. Kelber, W. Webber, G. K. Gomes, M. Lohmann, M. S. Rodrigues, D. Ledur","doi":"10.1109/IVS.2004.1336376","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336376","url":null,"abstract":"Drive-by-wire systems have been establishing the technological basis that is opening opportunities for the development of new driver assistance and safety systems, making it possible even for a computer to drive or park a car. Driving a car by using just electronic signals opens also possibilities for the development of new human machine interfaces (H.M.I.) that can eventually substitute the current steering wheel and pedals structure. For some physically handicapped people, however, this signifies the possibility of driving the family's car by just attaching the appropriate H.M.I. on it, which could be, for example, a joystick. In this article the use of a joystick as H.M.I, and its relation to the vehicle dynamics is analyzed, and to overcome possible \"fishtailing movements\" an active steering unit with integrated ACC feature, incorporated to the joystick, is proposed.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"14 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":"133599524","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.2004.1336492
Mathieu St-Pierre, Mathieu, S. t-Pierre, D. Gingras
An integrated navigation information system must know continuously the current position with a good precision. The required performance of the positioning module is achieved by using a cluster of heterogeneous sensors whose measurements are fused. The most popular data fusion method for positioning problems is the extended Kalman filter. The extended Kalman filter is a variation of the Kalman filter used to solve non-linear problems. Recently, an improvement to the extended Kalman filter has been proposed, the unscented Kalman filter. This paper describes an empirical analysis evaluating the performances of the unscented Kalman filter and comparing them with the extended Kalman filter's performances.
{"title":"Comparison between the unscented Kalman filter and the extended Kalman filter for the position estimation module of an integrated navigation information system","authors":"Mathieu St-Pierre, Mathieu, S. t-Pierre, D. Gingras","doi":"10.1109/IVS.2004.1336492","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336492","url":null,"abstract":"An integrated navigation information system must know continuously the current position with a good precision. The required performance of the positioning module is achieved by using a cluster of heterogeneous sensors whose measurements are fused. The most popular data fusion method for positioning problems is the extended Kalman filter. The extended Kalman filter is a variation of the Kalman filter used to solve non-linear problems. Recently, an improvement to the extended Kalman filter has been proposed, the unscented Kalman filter. This paper describes an empirical analysis evaluating the performances of the unscented Kalman filter and comparing them with the extended Kalman filter's performances.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"58 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":"116527480","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.2004.1336429
A. Kun, W. Miller, A. Pelhe, R. Lynch
Project54 is a research and development effort that involves integrating electronic devices in police cruisers into a single system. Officers primarily interact with the Project54 system through its voice interface. The Project54 system software architecture is completely modular and is based on Microsoft's Component Object Model (COM). The software includes specialized modules that allow interfacing to commercial speech recognition (SR) and text-to-speech (ITS) engines. Modules can communicate by means of one-to-one text messaging. Recognition results from the SR engine are routed to the appropriate destination application using text messages. Similarly, speech output requests are routed from applications to the TTS engine in the form of text messages. The system is currently used in over 100 cruisers of the New Hampshire State Police and other police departments in New Hampshire.
{"title":"A software architecture supporting in-car speech interaction","authors":"A. Kun, W. Miller, A. Pelhe, R. Lynch","doi":"10.1109/IVS.2004.1336429","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336429","url":null,"abstract":"Project54 is a research and development effort that involves integrating electronic devices in police cruisers into a single system. Officers primarily interact with the Project54 system through its voice interface. The Project54 system software architecture is completely modular and is based on Microsoft's Component Object Model (COM). The software includes specialized modules that allow interfacing to commercial speech recognition (SR) and text-to-speech (ITS) engines. Modules can communicate by means of one-to-one text messaging. Recognition results from the SR engine are routed to the appropriate destination application using text messages. Similarly, speech output requests are routed from applications to the TTS engine in the form of text messages. The system is currently used in over 100 cruisers of the New Hampshire State Police and other police departments in New Hampshire.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"46 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":"114569140","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：