Pub Date : 2005-06-06DOI: 10.1109/IVS.2005.1505091
F. Arnell, L. Petersson
Segmentation of the scene is a fundamental component in computer vision to find regions of interest. Most systems that aspire to run in real-time use a fast segmentation stage that considers the whole image, and then a more costly stage for classification. In this paper we present a novel approach to segment moving objects from images taken with a moving camera. The segmentation algorithm is based on a special representation of optical flow, on which u-disparity is applied. The u-disparity is used to indirectly find and mask out the background flow in the image, by approximating it with a quadratic function. Robustness in the optical flow calculation is achieved by contrast content filtering. The algorithm successfully segments moving pedestrians from a moving vehicle with few false positive segments. Most false positive segments are due to poles and organic structures, such as trees. Such false positives are, however, easily rejected in a classification stage. The presented segmentation algorithm is intended to be used as a component in a detection/classification framework.
{"title":"Fast object segmentation from a moving camera","authors":"F. Arnell, L. Petersson","doi":"10.1109/IVS.2005.1505091","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505091","url":null,"abstract":"Segmentation of the scene is a fundamental component in computer vision to find regions of interest. Most systems that aspire to run in real-time use a fast segmentation stage that considers the whole image, and then a more costly stage for classification. In this paper we present a novel approach to segment moving objects from images taken with a moving camera. The segmentation algorithm is based on a special representation of optical flow, on which u-disparity is applied. The u-disparity is used to indirectly find and mask out the background flow in the image, by approximating it with a quadratic function. Robustness in the optical flow calculation is achieved by contrast content filtering. The algorithm successfully segments moving pedestrians from a moving vehicle with few false positive segments. Most false positive segments are due to poles and organic structures, such as trees. Such false positives are, however, easily rejected in a classification stage. The presented segmentation algorithm is intended to be used as a component in a detection/classification framework.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122964182","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505150
L. Fletcher, L. Petersson, A. Zelinsky
Automated fatigue detection devices show much promise in combating fatigue related accidents. One aspect which hampers the introduction of these technologies is context awareness. In this paper we develop and evaluate a road scene monotony detector. The detector can be used to give context awareness to fatigue detection tools to minimise false positives. The approach could also be used by road makers to quantify monotony on fatigue prone stretches of road. The detector uses MPEG compression to measure the change in information content of the road scene over time. We show that the detector correlates highly with human identified monotonous scenes. The technique is consistent over time and applicable for day and night operation. The compression is augmented with lane tracking data to distinguish between otherwise difficult cases. The detector is integrated into a fatigue management driver assistance system.
{"title":"Road scene monotony detection in a fatigue management driver assistance system","authors":"L. Fletcher, L. Petersson, A. Zelinsky","doi":"10.1109/IVS.2005.1505150","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505150","url":null,"abstract":"Automated fatigue detection devices show much promise in combating fatigue related accidents. One aspect which hampers the introduction of these technologies is context awareness. In this paper we develop and evaluate a road scene monotony detector. The detector can be used to give context awareness to fatigue detection tools to minimise false positives. The approach could also be used by road makers to quantify monotony on fatigue prone stretches of road. The detector uses MPEG compression to measure the change in information content of the road scene over time. We show that the detector correlates highly with human identified monotonous scenes. The technique is consistent over time and applicable for day and night operation. The compression is augmented with lane tracking data to distinguish between otherwise difficult cases. The detector is integrated into a fatigue management driver assistance system.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131455079","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505193
Y. Suda, Y. Takahashi, M. Kuwahara, S. Tanaka, K. Ikeuchi, M. Kagesawa, T. Shraishi, M. Onuki, K. Honda, M. Kano
In the sustainable ITS project at the Center for Collaborative Research, the University of Tokyo, an experiment platform is developed for drivers' characteristics analysis on the moving-based driving simulator. In the upper-level microscopic car traffic flow simulator, a prototype driver model and vehicle dynamics model are developed with flexibility in the upgrading process. For realistic human factor measurement experiments, our driving simulator is equipped with a frame-structured flexible cut-body cabin, 360 degrees-field-of-view omni directional projection type visual display system, a steering wheel with an AC servo motor, 6.1 ch surround audio system and 6 DOF motion system with turning table. Some measurement experiments are made on a highway with a real car, aimed at driving simulator validation. Understanding of individual driver's behavior on this platform will contribute to design of safe and comfortable driving environments.
{"title":"Development of universal driving simulator with interactive traffic environment","authors":"Y. Suda, Y. Takahashi, M. Kuwahara, S. Tanaka, K. Ikeuchi, M. Kagesawa, T. Shraishi, M. Onuki, K. Honda, M. Kano","doi":"10.1109/IVS.2005.1505193","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505193","url":null,"abstract":"In the sustainable ITS project at the Center for Collaborative Research, the University of Tokyo, an experiment platform is developed for drivers' characteristics analysis on the moving-based driving simulator. In the upper-level microscopic car traffic flow simulator, a prototype driver model and vehicle dynamics model are developed with flexibility in the upgrading process. For realistic human factor measurement experiments, our driving simulator is equipped with a frame-structured flexible cut-body cabin, 360 degrees-field-of-view omni directional projection type visual display system, a steering wheel with an AC servo motor, 6.1 ch surround audio system and 6 DOF motion system with turning table. Some measurement experiments are made on a highway with a real car, aimed at driving simulator validation. Understanding of individual driver's behavior on this platform will contribute to design of safe and comfortable driving environments.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131480685","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505207
Runmei Li, Wei Li
In this paper, the applications of genetic algorithms to dynamic traffic assignment are analyzed based on a dynamic traffic assignment variational inequality model and the condition of physical queue is studied in this model. A simple example is used to demonstrate the efficiency of the genetic algorithms. The conclusions and directions for future development about the application of genetic algorithm to traffic assignment are presented.
{"title":"The application of genetic algorithm to dynamic traffic assignment","authors":"Runmei Li, Wei Li","doi":"10.1109/IVS.2005.1505207","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505207","url":null,"abstract":"In this paper, the applications of genetic algorithms to dynamic traffic assignment are analyzed based on a dynamic traffic assignment variational inequality model and the condition of physical queue is studied in this model. A simple example is used to demonstrate the efficiency of the genetic algorithms. The conclusions and directions for future development about the application of genetic algorithm to traffic assignment are presented.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131496756","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505137
Qiqian Zhang, Hui Qian, Miaoliang Zhu
Because of the complexity of the outdoor terrain and the variety of the robot missions, the autonomous mobile robots (AMR) have to carry out missions in unstructured and impossibly predicted environment. The acquisition of accurate environment parameters is crucial for robot path planning. In this article, the idea of mission-plan is introduced on the basis of the path plan. The whole mission is decomposed into several sub-missions during the mission modeling process. And one case-based mission-planning method (CBMP) is applied to filter and optimize the robot's geometric and kinetic parameters for properly configuration. At last, a proving ground is to validate the parameter adaptation of CBMP algorithm.
{"title":"Parameter adaptation by case-based mission-planning of outdoor autonomous mobile robot","authors":"Qiqian Zhang, Hui Qian, Miaoliang Zhu","doi":"10.1109/IVS.2005.1505137","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505137","url":null,"abstract":"Because of the complexity of the outdoor terrain and the variety of the robot missions, the autonomous mobile robots (AMR) have to carry out missions in unstructured and impossibly predicted environment. The acquisition of accurate environment parameters is crucial for robot path planning. In this article, the idea of mission-plan is introduced on the basis of the path plan. The whole mission is decomposed into several sub-missions during the mission modeling process. And one case-based mission-planning method (CBMP) is applied to filter and optimize the robot's geometric and kinetic parameters for properly configuration. At last, a proving ground is to validate the parameter adaptation of CBMP algorithm.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131532784","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505138
E. Seignez, A. Lambert, T. Maurin
In this paper, we consider a parking method for autonomous vehicle in an underground car park. The implemented method is decomposed into three tasks. Starting from configuration given by the vehicle owner, the first one is the motion control of the vehicle from his residence to the car park. After joining the underground car park thanks to the implementation of a path tracking method, the next step is the scrutation of a free space in the car park followed by the operations used for the parking maneuver. The last one, during all the previously seen stages, is the localization mechanisms that allows the vehicle to keep a correct position in the global frame during the whole displacement.
{"title":"Autonomous parking carrier for intelligent vehicle","authors":"E. Seignez, A. Lambert, T. Maurin","doi":"10.1109/IVS.2005.1505138","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505138","url":null,"abstract":"In this paper, we consider a parking method for autonomous vehicle in an underground car park. The implemented method is decomposed into three tasks. Starting from configuration given by the vehicle owner, the first one is the motion control of the vehicle from his residence to the car park. After joining the underground car park thanks to the implementation of a path tracking method, the next step is the scrutation of a free space in the car park followed by the operations used for the parking maneuver. The last one, during all the previously seen stages, is the localization mechanisms that allows the vehicle to keep a correct position in the global frame during the whole displacement.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126809521","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505088
H. Hattori, N. Takeda
We propose a new domain-specific area-based stereo method that is applicable to various tasks including safe navigation and pedestrian detection. Incorporating a spatial restriction in the height direction of road scenes into the recursive computation of correlation measures, the proposed method efficiently provides dense disparity measures. A pair of cameras just has to be weakly calibrated due to the non-metric formulation. We also implement our stereo method on a newly developed onboard LSI, which has a dedicated architecture for practical automotive use and realizes more than BOM disparity estimations per second. Furthermore, we apply our method to a side collision warning system, which detects approaching objects such as pedestrians and bicycles. Through experiments we demonstrate the efficiency of our stereo method in road environments.
{"title":"Dense stereo matching in restricted disparity space","authors":"H. Hattori, N. Takeda","doi":"10.1109/IVS.2005.1505088","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505088","url":null,"abstract":"We propose a new domain-specific area-based stereo method that is applicable to various tasks including safe navigation and pedestrian detection. Incorporating a spatial restriction in the height direction of road scenes into the recursive computation of correlation measures, the proposed method efficiently provides dense disparity measures. A pair of cameras just has to be weakly calibrated due to the non-metric formulation. We also implement our stereo method on a newly developed onboard LSI, which has a dedicated architecture for practical automotive use and realizes more than BOM disparity estimations per second. Furthermore, we apply our method to a side collision warning system, which detects approaching objects such as pedestrians and bicycles. Through experiments we demonstrate the efficiency of our stereo method in road environments.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126893272","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505147
Andreas D. Lattner, Jan D. Gehrke, I. Timm, O. Herzog
Recent advances in the field of intelligent vehicles have shown that it is possible nowadays to provide the driver with useful assistance systems, or even letting a car drive autonomously over long distances on highways. Usually these approaches are on a rather quantitative level. A knowledge-based approach as presented here has the advantage of a better comprehensibility and allows for formulating and using common sense knowledge and traffic rules while reasoning. In our approach a knowledge base is the central component for higher-level functionality. A qualitative mapping module abstracts from the quantitative data and stores symbolic facts in the knowledge base. The knowledge-based approach allows for easily integrating and adjusting background knowledge. Higher-level modules can query the knowledge base in order to evaluate the situation and decide what actions to perform. For the evaluation of the approach a prototype was developed in order to simulate traffic scenarios. In experiments behavior decision was applied for controlling the vehicle and its gaze.
{"title":"A knowledge-based approach to behavior decision in intelligent vehicles","authors":"Andreas D. Lattner, Jan D. Gehrke, I. Timm, O. Herzog","doi":"10.1109/IVS.2005.1505147","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505147","url":null,"abstract":"Recent advances in the field of intelligent vehicles have shown that it is possible nowadays to provide the driver with useful assistance systems, or even letting a car drive autonomously over long distances on highways. Usually these approaches are on a rather quantitative level. A knowledge-based approach as presented here has the advantage of a better comprehensibility and allows for formulating and using common sense knowledge and traffic rules while reasoning. In our approach a knowledge base is the central component for higher-level functionality. A qualitative mapping module abstracts from the quantitative data and stores symbolic facts in the knowledge base. The knowledge-based approach allows for easily integrating and adjusting background knowledge. Higher-level modules can query the knowledge base in order to evaluate the situation and decide what actions to perform. For the evaluation of the approach a prototype was developed in order to simulate traffic scenarios. In experiments behavior decision was applied for controlling the vehicle and its gaze.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123207491","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505217
Yuan Sun, F.-Y. Wang
The open vehicular industry standard OSEK/VDX is introduced briefly and an OSEK/VDX-based architecture for vehicular application specific embedded operating systems are proposed in this paper. This architecture is designed based on a microkernel mode since its flexibility, reliability and portability are critical to the safety and performance of vehicles. Finally, the UML is used to model the architecture of vehicular application specific embedded operating systems. Through analyzing the functions and the proposed relationships among different components, the feasibility of constructing a Linux-based vehicular application specific embedded operating system is demonstrated.
{"title":"A design architecture for OSEK/VDX-based vehicular application specific embedded operating systems","authors":"Yuan Sun, F.-Y. Wang","doi":"10.1109/IVS.2005.1505217","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505217","url":null,"abstract":"The open vehicular industry standard OSEK/VDX is introduced briefly and an OSEK/VDX-based architecture for vehicular application specific embedded operating systems are proposed in this paper. This architecture is designed based on a microkernel mode since its flexibility, reliability and portability are critical to the safety and performance of vehicles. Finally, the UML is used to model the architecture of vehicular application specific embedded operating systems. Through analyzing the functions and the proposed relationships among different components, the feasibility of constructing a Linux-based vehicular application specific embedded operating system is demonstrated.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114550120","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 : 2005-06-06DOI: 10.1109/IVS.2005.1505125
Wei-Han Liu, Chieh-Cheng Cheng, Jwusheng Hu
In this work, a robust speaker's location estimation method in a vehicle environment is presented. This method applies Gaussian mixture models (GMM) to the phase information obtained from a microphone array. The individual Gaussian component of a GMM represents some general location-dependent phase difference distribution between two microphones. These distributions are effective in modeling the speaker's location. The relation between geometry of microphone array and frequency band is taken into consideration to avoid aliasing problems. The proposed approach provides an accurate estimation even in near-field, noisy and complex vehicle environment. Moreover, it performs well not only in non-line-of-sight cases, but also in the conditions that the speakers are aligned in a direction to the microphone array with difference distances. Experiments are conducted in a mini-van vehicle and the results show that the proposed method outperform the popular technique multiple signal classification method (MUSIC) in different SNR cases.
{"title":"Robust speaker's location estimation in a vehicle environment using GMM models","authors":"Wei-Han Liu, Chieh-Cheng Cheng, Jwusheng Hu","doi":"10.1109/IVS.2005.1505125","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505125","url":null,"abstract":"In this work, a robust speaker's location estimation method in a vehicle environment is presented. This method applies Gaussian mixture models (GMM) to the phase information obtained from a microphone array. The individual Gaussian component of a GMM represents some general location-dependent phase difference distribution between two microphones. These distributions are effective in modeling the speaker's location. The relation between geometry of microphone array and frequency band is taken into consideration to avoid aliasing problems. The proposed approach provides an accurate estimation even in near-field, noisy and complex vehicle environment. Moreover, it performs well not only in non-line-of-sight cases, but also in the conditions that the speakers are aligned in a direction to the microphone array with difference distances. Experiments are conducted in a mini-van vehicle and the results show that the proposed method outperform the popular technique multiple signal classification method (MUSIC) in different SNR cases.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115911946","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：