Pub Date : 2005-06-06DOI: 10.1109/IVS.2005.1505219
Lin Zhu, Jingyan Song, Qiao Huang, Mingjie Zhang, H. Liu
Video surveillance technology has been widely used in intelligent transportation system (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov random field (MRF) based tracking model through a kind of special structuring elements in mathematical morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.
{"title":"A novel module of tracking vehicles with occlusion","authors":"Lin Zhu, Jingyan Song, Qiao Huang, Mingjie Zhang, H. Liu","doi":"10.1109/IVS.2005.1505219","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505219","url":null,"abstract":"Video surveillance technology has been widely used in intelligent transportation system (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov random field (MRF) based tracking model through a kind of special structuring elements in mathematical morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"1 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":"130840874","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.2005.1505085
F. Bu, C. Chan
Pedestrian safety is a primary traffic issue in urban environment. The use of modern sensing technologies to improve pedestrian safety has remained an active research topic for years. A variety of sensing technologies have been developed for pedestrian detection. The application of pedestrian detection on transit vehicle platforms is desirable and feasible in the near future. In this paper, potential sensing technologies are first reviewed for their advantages and limitations. Several sensors are then chosen for further experimental testing and evaluation. A reliable sensing system will require a combination of multiple sensors to deal with near-range in stationary conditions and longer-range detection in moving conditions. An approach of vehicle-infrastructure integrated solution is suggested for the pedestrian detection in transit bus application.
{"title":"Pedestrian detection in transit bus application: sensing technologies and safety solutions","authors":"F. Bu, C. Chan","doi":"10.1109/IVS.2005.1505085","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505085","url":null,"abstract":"Pedestrian safety is a primary traffic issue in urban environment. The use of modern sensing technologies to improve pedestrian safety has remained an active research topic for years. A variety of sensing technologies have been developed for pedestrian detection. The application of pedestrian detection on transit vehicle platforms is desirable and feasible in the near future. In this paper, potential sensing technologies are first reviewed for their advantages and limitations. Several sensors are then chosen for further experimental testing and evaluation. A reliable sensing system will require a combination of multiple sensors to deal with near-range in stationary conditions and longer-range detection in moving conditions. An approach of vehicle-infrastructure integrated solution is suggested for the pedestrian detection in transit bus application.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"1 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":"129241142","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.2005.1505179
Hongchao Liu, Jingyan Song, Yafeng Yin
Traffic signals may induce unexpected bottlenecks when queues from an intersection spill back and block its adjacent upstream intersection. The information of whether and when queues from the downstream intersection would reach the upstream intersection is of particular significance to signal tuning of closely spaced oversaturated intersections. This paper presents a macroscopic simulation approach to emulate the formation and propagation of backward and forward waves along closely spaced traffic signals and demonstrates its application to the evaluation of point queue based signal timing plans.
{"title":"A simplified method for estimation of back of queue and its application in macroscopic simulation","authors":"Hongchao Liu, Jingyan Song, Yafeng Yin","doi":"10.1109/IVS.2005.1505179","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505179","url":null,"abstract":"Traffic signals may induce unexpected bottlenecks when queues from an intersection spill back and block its adjacent upstream intersection. The information of whether and when queues from the downstream intersection would reach the upstream intersection is of particular significance to signal tuning of closely spaced oversaturated intersections. This paper presents a macroscopic simulation approach to emulate the formation and propagation of backward and forward waves along closely spaced traffic signals and demonstrates its application to the evaluation of point queue based signal timing plans.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"73 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":"126356966","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.2005.1505070
D. Linzmeier, D. Vogt, P. Prasanna
Whenever addressing pedestrian related injury focal points in automotive accidentology, a comprehensive approach comprising both active and passive safety elements should be followed. Passive safety short term solutions can be contact sensor systems that trigger raisable engine hoods and an active safety element could be the brake assist. However, an important enabler for a future pedestrian protection system is a suitable, low-cost, environment-friendly sensing technology for pedestrian detection, supported by a fast and reliable algorithm for object localization. This paper discusses such an innovative approach for pedestrian detection and localization, by presenting a system based on an array of passive infrared thermopile sensors, aided with probabilistic techniques for detection improvement. The distributed thermopile sensors (sensor-array) detect the object presence within their respective field-of-view independently from each other. These measurements are then validated and fused using a mathematical framework. The focus of this paper is on the signal interpretation of the thermopile sensors. Since passive thermopile sensors are prone to background influences and can detect only the relative temperature changes, a robust signal-interpretation algorithm is essential. In this respect, a statistical approach combining Dempster-Shafer-theory with occupancy-grid method is used to achieve reliable pedestrian detection. The performance of the proposed approach is discussed by presenting some experimental results.
{"title":"Probabilistic signal interpretation methods for a thermopile pedestrian detection system","authors":"D. Linzmeier, D. Vogt, P. Prasanna","doi":"10.1109/IVS.2005.1505070","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505070","url":null,"abstract":"Whenever addressing pedestrian related injury focal points in automotive accidentology, a comprehensive approach comprising both active and passive safety elements should be followed. Passive safety short term solutions can be contact sensor systems that trigger raisable engine hoods and an active safety element could be the brake assist. However, an important enabler for a future pedestrian protection system is a suitable, low-cost, environment-friendly sensing technology for pedestrian detection, supported by a fast and reliable algorithm for object localization. This paper discusses such an innovative approach for pedestrian detection and localization, by presenting a system based on an array of passive infrared thermopile sensors, aided with probabilistic techniques for detection improvement. The distributed thermopile sensors (sensor-array) detect the object presence within their respective field-of-view independently from each other. These measurements are then validated and fused using a mathematical framework. The focus of this paper is on the signal interpretation of the thermopile sensors. Since passive thermopile sensors are prone to background influences and can detect only the relative temperature changes, a robust signal-interpretation algorithm is essential. In this respect, a statistical approach combining Dempster-Shafer-theory with occupancy-grid method is used to achieve reliable pedestrian detection. The performance of the proposed approach is discussed by presenting some experimental results.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"6 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":"126401706","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.2005.1505079
F. Woelk, I. Schiller, R. Koch
Mobile tracking systems are of wide interest. For instance sport photographers often hire helicopters to obtain close range images of e.g. aquatic athletes. Besides the high price for hiring a helicopter, good helicopter pilots are not everywhere available. One way to circumvent these problems is the use of a cheap model helicopter. Since flying a model helicopter is a demanding task, there are either two persons needed for the operation of the system (one person for steering the helicopter and the other for the operation of the camera), or alternatively an automatic tracking system can be used. In this work an automatic, image based tracking system is described. The algorithm combines color histograms as similarity measures with a particle filter and achieves fast and robust tracking results. A novel method for fast histogram computation is proposed. The system keeps the object of interest automatically in the viewing field of the camera so that the only task left to the camera operator is to initiate the imaging process. This simple task can be additionally managed by the helicopter pilot so that a single person is sufficient to steer the helicopter and to take the images.
{"title":"An airborne Bayesian color tracking system","authors":"F. Woelk, I. Schiller, R. Koch","doi":"10.1109/IVS.2005.1505079","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505079","url":null,"abstract":"Mobile tracking systems are of wide interest. For instance sport photographers often hire helicopters to obtain close range images of e.g. aquatic athletes. Besides the high price for hiring a helicopter, good helicopter pilots are not everywhere available. One way to circumvent these problems is the use of a cheap model helicopter. Since flying a model helicopter is a demanding task, there are either two persons needed for the operation of the system (one person for steering the helicopter and the other for the operation of the camera), or alternatively an automatic tracking system can be used. In this work an automatic, image based tracking system is described. The algorithm combines color histograms as similarity measures with a particle filter and achieves fast and robust tracking results. A novel method for fast histogram computation is proposed. The system keeps the object of interest automatically in the viewing field of the camera so that the only task left to the camera operator is to initiate the imaging process. This simple task can be additionally managed by the helicopter pilot so that a single person is sufficient to steer the helicopter and to take the images.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"32 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":"121670059","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.2005.1505096
Ching-yao Chan, BCnedicte Bougler
Intersection collisions represent a significant portion of highway accidents. Recent research and development activities have suggested potential solutions to address this critical safety issue by supplying timely alerts to drivers of imminent collisions. These intersection decision support systems utilized sensor, communication and computer technologies to help drivers recognize risky conditions, thus actions can be taken to avoid collisions. A cooperative vehicle-infrastructure concept, built upon such premises, seek to combine the information available from vehicles and roadside in a synergistic framework so that a flexible yet sensible system can be deployed in the near future. The work presented in this paper represents an experimental effort conducted at a real-world intersection, by the use of an instrumented vehicle and roadside traffic monitoring, to explore technical challenges encountered in a vehicle-infrastructure integration approach.
{"title":"Evaluation of cooperative roadside and vehicle-based data collection for assessing intersection conflicts","authors":"Ching-yao Chan, BCnedicte Bougler","doi":"10.1109/IVS.2005.1505096","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505096","url":null,"abstract":"Intersection collisions represent a significant portion of highway accidents. Recent research and development activities have suggested potential solutions to address this critical safety issue by supplying timely alerts to drivers of imminent collisions. These intersection decision support systems utilized sensor, communication and computer technologies to help drivers recognize risky conditions, thus actions can be taken to avoid collisions. A cooperative vehicle-infrastructure concept, built upon such premises, seek to combine the information available from vehicles and roadside in a synergistic framework so that a flexible yet sensible system can be deployed in the near future. The work presented in this paper represents an experimental effort conducted at a real-world intersection, by the use of an instrumented vehicle and roadside traffic monitoring, to explore technical challenges encountered in a vehicle-infrastructure integration approach.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"3 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":"125058147","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.2005.1505198
Antoni B. Chan, N. Vasconcelos
We propose to model the traffic flow in a video using a holistic generative model that does not require segmentation or tracking. In particular, we adopt the dynamic texture model, an auto-regressive stochastic process, which encodes the appearance and the underlying motion separately into two probability distributions. With this representation, retrieval of similar video sequences and classification of traffic congestion can be performed using the Kullback-Leibler divergence and the Martin distance. Experimental results show good retrieval and classification performance, with robustness to environmental conditions such as variable lighting and shadows.
{"title":"Classification and retrieval of traffic video using auto-regressive stochastic processes","authors":"Antoni B. Chan, N. Vasconcelos","doi":"10.1109/IVS.2005.1505198","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505198","url":null,"abstract":"We propose to model the traffic flow in a video using a holistic generative model that does not require segmentation or tracking. In particular, we adopt the dynamic texture model, an auto-regressive stochastic process, which encodes the appearance and the underlying motion separately into two probability distributions. With this representation, retrieval of similar video sequences and classification of traffic congestion can be performed using the Kullback-Leibler divergence and the Martin distance. Experimental results show good retrieval and classification performance, with robustness to environmental conditions such as variable lighting and shadows.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"356 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":"131337024","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.2005.1505184
A. Kapp
This article addresses the problem of robust signal processing of 3D lidar data prone to noise. After describing the characteristics of the lidar data given we describe how the data can be segmented in a robust manner. The approach is based on edge detection followed by region growing. We show how the segments can be described using parametric models. In the final step the segments are circumscribed using appropriate bounding objects. We motivate the individual steps of our approach and light up the mathematical background.
{"title":"Robust object segmentation and parametrization of 3D lidar data","authors":"A. Kapp","doi":"10.1109/IVS.2005.1505184","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505184","url":null,"abstract":"This article addresses the problem of robust signal processing of 3D lidar data prone to noise. After describing the characteristics of the lidar data given we describe how the data can be segmented in a robust manner. The approach is based on edge detection followed by region growing. We show how the segments can be described using parametric models. In the final step the segments are circumscribed using appropriate bounding objects. We motivate the individual steps of our approach and light up the mathematical background.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"13 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":"115468753","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.2005.1505170
P. Gil-Jiménez, S. Lafuente-Arroyo, H. Gómez-Moreno, F. López-Ferreras, S. Maldonado-Bascón
In this paper we have developed a new algorithm of artificial vision oriented to traffic sign shape classification. The classification method basically consists of a series of comparison between the FFT of the signature of a blob and the FFT of the signatures of the reference shapes used in traffic signs. The two major steps of the process are: the segmentation according to the color and the identification of the geometry of the candidate blob using its signature. The most important advances are its robustness against rotation and deformation due to camera projections.
{"title":"Traffic sign shape classification evaluation. Part II. FFT applied to the signature of blobs","authors":"P. Gil-Jiménez, S. Lafuente-Arroyo, H. Gómez-Moreno, F. López-Ferreras, S. Maldonado-Bascón","doi":"10.1109/IVS.2005.1505170","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505170","url":null,"abstract":"In this paper we have developed a new algorithm of artificial vision oriented to traffic sign shape classification. The classification method basically consists of a series of comparison between the FFT of the signature of a blob and the FFT of the signatures of the reference shapes used in traffic signs. The two major steps of the process are: the segmentation according to the color and the identification of the geometry of the candidate blob using its signature. The most important advances are its robustness against rotation and deformation due to camera projections.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"6 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":"123809478","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.2005.1505163
S. Chiricescu, S. Chai, K. Moat, B. Lucas, P. May, J. Norm, R. Essick, M. Schuette
A large number of sensors (i.e., video, radar, laser, ultrasound, etc.) that continuously monitor the environment are finding their way in the average automobile. The algorithms processing the data captured by these sensors are streaming in nature and require a high rate of computation. Due to the characteristics of the automotive environment, this computation has to be delivered under very low energy and cost budgets. The reconfigurable streaming vector processing (RSVP/spl trade/) architecture is a vector coprocessor architecture which accelerates streaming data processing. This paper presents the RSVP architecture and its second implementation, RSVP II. Our results show significant speedups on data streaming functions running compiled code. On a lane tracking application, RSVP II shows impressive performance results. From a performance/$ and performance/mW perspective, RSVP architecture compares favorably with leading DSP architectures. The time to market is substantially reduced due to ease of programmability, elimination of hand-tuned assembly code, and support for software re-use through binary compatibility across multiple implementations.
{"title":"RSVP II: a next generation automotive vector processor","authors":"S. Chiricescu, S. Chai, K. Moat, B. Lucas, P. May, J. Norm, R. Essick, M. Schuette","doi":"10.1109/IVS.2005.1505163","DOIUrl":"https://doi.org/10.1109/IVS.2005.1505163","url":null,"abstract":"A large number of sensors (i.e., video, radar, laser, ultrasound, etc.) that continuously monitor the environment are finding their way in the average automobile. The algorithms processing the data captured by these sensors are streaming in nature and require a high rate of computation. Due to the characteristics of the automotive environment, this computation has to be delivered under very low energy and cost budgets. The reconfigurable streaming vector processing (RSVP/spl trade/) architecture is a vector coprocessor architecture which accelerates streaming data processing. This paper presents the RSVP architecture and its second implementation, RSVP II. Our results show significant speedups on data streaming functions running compiled code. On a lane tracking application, RSVP II shows impressive performance results. From a performance/$ and performance/mW perspective, RSVP architecture compares favorably with leading DSP architectures. The time to market is substantially reduced due to ease of programmability, elimination of hand-tuned assembly code, and support for software re-use through binary compatibility across multiple implementations.","PeriodicalId":386189,"journal":{"name":"IEEE Proceedings. Intelligent Vehicles Symposium, 2005.","volume":"83 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":"126176227","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：