Pub Date : 2004-06-14DOI: 10.1109/IVS.2004.1336455
A. Eidehall, Fredrik Gustafsson
Detection and tracking of other vehicles and lane geometry will be required for many future intelligent driver assistance systems. By integrating the estimation of these two features into a single filter, a more optimal utilization of the available information can be achieved. For example, it is possible to improve the lane curvature estimate during bad visibility by studying the motion of other vehicles. This paper derives and evaluates various approximations that are needed in order to deal with the non-linearities that are introduced by such an approach.
{"title":"Combined road prediction and target tracking in collision avoidance","authors":"A. Eidehall, Fredrik Gustafsson","doi":"10.1109/IVS.2004.1336455","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336455","url":null,"abstract":"Detection and tracking of other vehicles and lane geometry will be required for many future intelligent driver assistance systems. By integrating the estimation of these two features into a single filter, a more optimal utilization of the available information can be achieved. For example, it is possible to improve the lane curvature estimate during bad visibility by studying the motion of other vehicles. This paper derives and evaluates various approximations that are needed in order to deal with the non-linearities that are introduced by such an approach.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"45 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":"132190617","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.2004.1336495
M. Koyamaishi, H. Sakai, T. Fujii, M. Tanimoto
In ITS development, it is expected that infrastructure maintenance of cameras or various sensors is carried out. For a system using those infrastructure, we have proposed the HIR (human-oriented information restructuring) System. This system assists driver's visual sense by integrating and restructuring different kinds of information. This paper contributes HIR algorithm, error of data, and required accuracy towards realization of HIR System. Furthermore, we built the system to acquire position and direction of in-vehicle camera. Based on their previous study, we test the effectiveness of our developed system architecture and made experiment in the situation of turning right at the actual intersection, not georama. As a result, we can generate visual assistant images and display them on the car monitor in real-time.
在智能交通系统的开发中，需要对摄像头或各种传感器进行基础设施维护。对于使用这些基础结构的系统，我们提出了HIR (human-oriented information restructuring)系统。该系统通过整合和重组不同类型的信息来帮助驾驶员的视觉感知。本文对HIR系统的实现提出了算法、数据误差和精度要求。在此基础上，构建了车载摄像机位置和方向采集系统。在前人研究的基础上，我们测试了我们开发的系统架构的有效性，并在实际十字路口右转的情况下进行了实验，而不是在georama。因此，我们可以生成视觉辅助图像，并将其实时显示在汽车监视器上。
{"title":"Acquisition of position and direction of in-vehicle camera for HIR system","authors":"M. Koyamaishi, H. Sakai, T. Fujii, M. Tanimoto","doi":"10.1109/IVS.2004.1336495","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336495","url":null,"abstract":"In ITS development, it is expected that infrastructure maintenance of cameras or various sensors is carried out. For a system using those infrastructure, we have proposed the HIR (human-oriented information restructuring) System. This system assists driver's visual sense by integrating and restructuring different kinds of information. This paper contributes HIR algorithm, error of data, and required accuracy towards realization of HIR System. Furthermore, we built the system to acquire position and direction of in-vehicle camera. Based on their previous study, we test the effectiveness of our developed system architecture and made experiment in the situation of turning right at the actual intersection, not georama. As a result, we can generate visual assistant images and display them on the car monitor in real-time.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"540 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":"133453638","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.2004.1336437
I. Puhlmann, S. Schussler, B. Hulin
The paper describes the latest improvements in the video-based obstacle detection system developed at Deutsche Bahn AG (Germany's leading railway operator). The system automatically detects obstacles in the pantograph gauge at a distance of up to 70 m and retracts the pantograph before collision with an obstacle. Due to the multitude of similar-looking objects within an epipolar line, the algorithms developed gives false obstacle warnings in over 0.7% of the images. With recognition of steady arms, the reliability of the system is improved considerably. With a constant detection ratio, false obstacle warnings can be reduced by 28%.
{"title":"Improvements on obstacle detection in the pantograph gauge due to the recognition of steady arms","authors":"I. Puhlmann, S. Schussler, B. Hulin","doi":"10.1109/IVS.2004.1336437","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336437","url":null,"abstract":"The paper describes the latest improvements in the video-based obstacle detection system developed at Deutsche Bahn AG (Germany's leading railway operator). The system automatically detects obstacles in the pantograph gauge at a distance of up to 70 m and retracts the pantograph before collision with an obstacle. Due to the multitude of similar-looking objects within an epipolar line, the algorithms developed gives false obstacle warnings in over 0.7% of the images. With recognition of steady arms, the reliability of the system is improved considerably. With a constant detection ratio, false obstacle warnings can be reduced by 28%.","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":"121776868","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.2004.1336445
T. Gandhi, M. Trivedi
Omni-directional cameras which give 360 degree panoramic view of the surroundings and have recently been used in many applications such as robotics, navigation and surveillance. This paper describes the application of motion estimation on omni camera to perform surround analysis using an automobile mounted camera. The system detects and tracks the surrounding vehicles by compensating the ego-motion and detecting objects having independent motion. Prior knowledge about ego-motion and calibration is optimally combined with the information from the image gradients to get better motion compensation.
{"title":"Motion based vehicle surround analysis using an omni-directional camera","authors":"T. Gandhi, M. Trivedi","doi":"10.1109/IVS.2004.1336445","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336445","url":null,"abstract":"Omni-directional cameras which give 360 degree panoramic view of the surroundings and have recently been used in many applications such as robotics, navigation and surveillance. This paper describes the application of motion estimation on omni camera to perform surround analysis using an automobile mounted camera. The system detects and tracks the surrounding vehicles by compensating the ego-motion and detecting objects having independent motion. Prior knowledge about ego-motion and calibration is optimally combined with the information from the image gradients to get better motion compensation.","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":"115165683","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.2004.1336424
J. Douret, R. Benosman
This paper deals with the issue of using multi-cameras for road traffic monitoring. The aim is to remove the classic monocular ambiguities and to retrieve the objects' height. An efficient and simple calibration method is introduced. It has the particularity to be connected to the geometry constraints of the road. The method relies on projective geometry and uses the structure of the plane at infinity. In a second stage, a high speed matching procedure is introduced. It is based on an altitude planar decomposition of the road scene. The method naturally achieves two tasks due to altitudes sampling. Match and reconstruction become simultaneous. Finally, experimental results are presented.
{"title":"A volumetric multi-cameras method dedicated to road traffic monitoring","authors":"J. Douret, R. Benosman","doi":"10.1109/IVS.2004.1336424","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336424","url":null,"abstract":"This paper deals with the issue of using multi-cameras for road traffic monitoring. The aim is to remove the classic monocular ambiguities and to retrieve the objects' height. An efficient and simple calibration method is introduced. It has the particularity to be connected to the geometry constraints of the road. The method relies on projective geometry and uses the structure of the plane at infinity. In a second stage, a high speed matching procedure is introduced. It is based on an altitude planar decomposition of the road scene. The method naturally achieves two tasks due to altitudes sampling. Match and reconstruction become simultaneous. Finally, experimental results are presented.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"189 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":"116334369","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.2004.1336407
S. Wender, O. Loehlein
Recently Viola et al. have described a fast and robust face detection system using Haar-Wavelet-like features, AdaBoost and a classifier cascade. This paper deals with some handicaps of AdaBoost and proposes some modifications to Viola's system. We then introduce a system for vehicle seat occupancy monitoring using an optical sensor.
{"title":"A cascade detector approach applied to vehicle occupant monitoring with an omni-directional camera","authors":"S. Wender, O. Loehlein","doi":"10.1109/IVS.2004.1336407","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336407","url":null,"abstract":"Recently Viola et al. have described a fast and robust face detection system using Haar-Wavelet-like features, AdaBoost and a classifier cascade. This paper deals with some handicaps of AdaBoost and proposes some modifications to Viola's system. We then introduce a system for vehicle seat occupancy monitoring using an optical sensor.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"9 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":"115438468","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.2004.1336357
Pini. Reisman Ofer, Mano Shai, Avidan Amnon
We present a real-time system that detects moving crowd in a video sequence. Crowd detection differs from pedestrian detection in that we assume that no individual pedestrian can be properly segmented in the image. We propose a scheme that looks at the motion patterns of crowd in the spatio-temporal domain and give an efficient implementation that can detect crowd in real-time. In our experiments we detected crowd at distances of up to 70 m.
{"title":"Crowd detection in video sequences","authors":"Pini. Reisman Ofer, Mano Shai, Avidan Amnon","doi":"10.1109/IVS.2004.1336357","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336357","url":null,"abstract":"We present a real-time system that detects moving crowd in a video sequence. Crowd detection differs from pedestrian detection in that we assume that no individual pedestrian can be properly segmented in the image. We propose a scheme that looks at the motion patterns of crowd in the spatio-temporal domain and give an efficient implementation that can detect crowd in real-time. In our experiments we detected crowd at distances of up to 70 m.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"10 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":"123672107","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.2004.1336413
M. Krodel, K. Kuhnert
Reinforcement learning (RL) is a method which provides true learning capabilities regarding situation-based actions. RL-systems explore and self-optimise actions for situations in a defined environment. This paper describes the research of a driver (assistance) system based on pure reinforcement learning in the framework of an autonomous vehicle. The target of this research is to determine to what extent RL-based systems serve as an enhancement or even an alternative to classical concepts of autonomous intelligent vehicles such as modelling or neural nets.
{"title":"Optimising situation-based behaviour of autonomous vehicles","authors":"M. Krodel, K. Kuhnert","doi":"10.1109/IVS.2004.1336413","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336413","url":null,"abstract":"Reinforcement learning (RL) is a method which provides true learning capabilities regarding situation-based actions. RL-systems explore and self-optimise actions for situations in a defined environment. This paper describes the research of a driver (assistance) system based on pure reinforcement learning in the framework of an autonomous vehicle. The target of this research is to determine to what extent RL-based systems serve as an enhancement or even an alternative to classical concepts of autonomous intelligent vehicles such as modelling or neural nets.","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":"130801084","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}
Incident information transmission using an IVC (Inter-Vehicle Communication) system is one of the most important features in ITS in order to increase safety and efficiency of road traffic. In IVC systems that use a spread spectrum communication (SS) scheme, it is necessary for each vehicle to know the PN code used to receive information and more than two equivalent PN codes must not be used in one communication area to avoid interference. Therefore, an appropriate scheme to assign a PN code to each communication under limited number of available PN codes. Especially it is necessary to assign PN codes efficiently to transmit incident information because it is very important for safety and many information transmissions are expected under an incident situation. Performance of incident information transmission based on the IVC system that assigns a PN code used by each vehicle to the absolute location on the road is analyzed. As the result of computer simulations, good performance is confirmed.
{"title":"An analysis of incident information transmission performance using an IVC system that assigns PN codes to the locations on the road","authors":"Takahiro Inoue Hisayoshi Nakata Makoto Itami Kohji Itoh","doi":"10.1109/IVS.2004.1336366","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336366","url":null,"abstract":"Incident information transmission using an IVC (Inter-Vehicle Communication) system is one of the most important features in ITS in order to increase safety and efficiency of road traffic. In IVC systems that use a spread spectrum communication (SS) scheme, it is necessary for each vehicle to know the PN code used to receive information and more than two equivalent PN codes must not be used in one communication area to avoid interference. Therefore, an appropriate scheme to assign a PN code to each communication under limited number of available PN codes. Especially it is necessary to assign PN codes efficiently to transmit incident information because it is very important for safety and many information transmissions are expected under an incident situation. Performance of incident information transmission based on the IVC system that assigns a PN code used by each vehicle to the absolute location on the road is analyzed. As the result of computer simulations, good performance is confirmed.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"65 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":"129363632","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：