Pub Date : 2004-06-14DOI: 10.1109/IVS.2004.1336403
Stefan Funck, Nikolaus Mohler, Wolfgang Oertel
We propose a system to estimate the occupancy of a car-park using a single image of a single camera. Very often car-parks are already equipped with CCTV-cameras for surveillance purposes which may be used for automatic detection systems as well. Our system is targeted on cases where occupancy values are sought, but exact solutions like automatic gates or induction loops are too costly and where estimate values are acceptable for the operator. The image processing for the vehicle classification basically works by constructing a reference image of the empty car-park given in the input image and then comparing those two. The occupancy estimate is determined by the vehicle to car-park pixel area ratio, where perspective distortion and occlusion is compensated.
{"title":"Determining car-park occupancy from single images","authors":"Stefan Funck, Nikolaus Mohler, Wolfgang Oertel","doi":"10.1109/IVS.2004.1336403","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336403","url":null,"abstract":"We propose a system to estimate the occupancy of a car-park using a single image of a single camera. Very often car-parks are already equipped with CCTV-cameras for surveillance purposes which may be used for automatic detection systems as well. Our system is targeted on cases where occupancy values are sought, but exact solutions like automatic gates or induction loops are too costly and where estimate values are acceptable for the operator. The image processing for the vehicle classification basically works by constructing a reference image of the empty car-park given in the input image and then comparing those two. The occupancy estimate is determined by the vehicle to car-park pixel area ratio, where perspective distortion and occlusion is compensated.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"16 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":"122267864","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.2004.1336389
H. Janssen, W. Niehsen
In this paper we propose a vehicle surround sensing system that combines information from a video sensor with a digital map sensor. The video sensor detects road signs and lane markers, whereas the digital map contains information on road geometry, topology and additional information attributes. We show both sensors to be complementary to each other and fuse their information to obtain driver assistance functions such as Speed Limit Assistant, Curve Warning System, and Hazard Warning System.
{"title":"Vehicle surround sensing based on information fusion of monocular video and digital map","authors":"H. Janssen, W. Niehsen","doi":"10.1109/IVS.2004.1336389","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336389","url":null,"abstract":"In this paper we propose a vehicle surround sensing system that combines information from a video sensor with a digital map sensor. The video sensor detects road signs and lane markers, whereas the digital map contains information on road geometry, topology and additional information attributes. We show both sensors to be complementary to each other and fuse their information to obtain driver assistance functions such as Speed Limit Assistant, Curve Warning System, and Hazard Warning System.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"31 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":"134585222","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.2004.1336446
Nick Barnes, A. Zelinsky
Algorithms for classifying road signs have a high computational cost per pixel processed. A promising approach to real-time sign detection is to reduce the number of pixels to be classified as being a particular sign to a minimum by some form of sign detection on the image using less time expensive algorithms. In this paper, we adapt the fast radial symmetry detector to the image stream from a camera mounted in a car eliminate almost all non-sign pixels from the image stream. We then are able to apply normalised cross-correlation to classify the signs. This method is suitable for circular signs only; we apply it to Australian speed signs in this paper. Our results show that it is robust to a broad range of lighting conditions. Also, as the method is fast, there is no need to make unrealistic-ally strict assumptions about image structure.
{"title":"Real-time radial symmetry for speed sign detection","authors":"Nick Barnes, A. Zelinsky","doi":"10.1109/IVS.2004.1336446","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336446","url":null,"abstract":"Algorithms for classifying road signs have a high computational cost per pixel processed. A promising approach to real-time sign detection is to reduce the number of pixels to be classified as being a particular sign to a minimum by some form of sign detection on the image using less time expensive algorithms. In this paper, we adapt the fast radial symmetry detector to the image stream from a camera mounted in a car eliminate almost all non-sign pixels from the image stream. We then are able to apply normalised cross-correlation to classify the signs. This method is suitable for circular signs only; we apply it to Australian speed signs in this paper. Our results show that it is robust to a broad range of lighting conditions. Also, as the method is fast, there is no need to make unrealistic-ally strict assumptions about image structure.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"45 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133008165","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.2004.1336497
Petr Ernest, Roman Maz, Libor Pfeueil
The paper describes a solution to railway vehicle localization problem for the cases, where no global positioning information (like GPS) is temporarily unavailable. The given solution also assumes no additional landmarks or other extraordinary installations aside the train track. The presented approach is based on smart fusion of onboard-gathered data making use of Kalman filter. The available data sources include a vehicle odometer and accelerometer.
{"title":"Train locator using inertial sensors and odometer","authors":"Petr Ernest, Roman Maz, Libor Pfeueil","doi":"10.1109/IVS.2004.1336497","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336497","url":null,"abstract":"The paper describes a solution to railway vehicle localization problem for the cases, where no global positioning information (like GPS) is temporarily unavailable. The given solution also assumes no additional landmarks or other extraordinary installations aside the train track. The presented approach is based on smart fusion of onboard-gathered data making use of Kalman filter. The available data sources include a vehicle odometer and accelerometer.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"32 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":"132589780","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.2004.1336387
U. Ozguner, K. Redmill, A. Broggi
The Defense Advanced Research Projects Agency (DARPA), is an agency of the United States Government, has issued a challenge to developers of off-road autonomous ground vehicles to design and build a vehicle that can complete a lengthy and difficult off road course across desert southwest areas of the United States. A one million dollar US prize is available to the team that completes the 200-250 mile course first and in less than 10 hours. This paper describes the Team TerraMax entry to the March, 2004 race event. Vehicle hardware and drive by wire actuators, internal and external sensing systems, sensor fusion, and high and low level control systems are described.
{"title":"Team TerraMax and the DARPA grand challenge: a general overview","authors":"U. Ozguner, K. Redmill, A. Broggi","doi":"10.1109/IVS.2004.1336387","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336387","url":null,"abstract":"The Defense Advanced Research Projects Agency (DARPA), is an agency of the United States Government, has issued a challenge to developers of off-road autonomous ground vehicles to design and build a vehicle that can complete a lengthy and difficult off road course across desert southwest areas of the United States. A one million dollar US prize is available to the team that completes the 200-250 mile course first and in less than 10 hours. This paper describes the Team TerraMax entry to the March, 2004 race event. Vehicle hardware and drive by wire actuators, internal and external sensing systems, sensor fusion, and high and low level control systems are described.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"314 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":"124452319","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.2004.1336505
A. Polychronopoulos, A. Amditis, E. Bekiaris
Hypovigilance detection and warning systems are currently based on stand alone sensor approaches. This paper presents a multisensor system that allows the information fusion of different sources (vehicle, driver and environmental sensing parameters) and contributes to the decrease of false alarms and misses of the hypovigilance detection system. A hybrid scheme- centralized communication and data flow management of integrated stand alone systems- is adopted, which in turn, allows the real time application to monitor the driver and provide imminent and information messages according to his/her state and adapted to the external traffic and environmental scenario. The data flow between all systems, sensors and modules is described to synthesize the functional architecture. The system development is funded by the European so-called AWAKE project.
{"title":"Information data flow in AWAKE multi-sensor driver monitoring system","authors":"A. Polychronopoulos, A. Amditis, E. Bekiaris","doi":"10.1109/IVS.2004.1336505","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336505","url":null,"abstract":"Hypovigilance detection and warning systems are currently based on stand alone sensor approaches. This paper presents a multisensor system that allows the information fusion of different sources (vehicle, driver and environmental sensing parameters) and contributes to the decrease of false alarms and misses of the hypovigilance detection system. A hybrid scheme- centralized communication and data flow management of integrated stand alone systems- is adopted, which in turn, allows the real time application to monitor the driver and provide imminent and information messages according to his/her state and adapted to the external traffic and environmental scenario. The data flow between all systems, sensors and modules is described to synthesize the functional architecture. The system development is funded by the European so-called AWAKE project.","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":"129928426","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.2004.1336381
S. Chiricescu, M. Schuette, R. Essick, B. Lucas, P. May, K. Moat, J. Norris
A myriad of sensors (i.e., video, radar, laser, ultrasound, etc.) continuously monitoring the environment are incorporated in future automobiles. The algorithms processing the data captured by these sensors are streaming in nature and require high levels of processing power. Due to the characteristics of the automotive market, this processing power has to be delivered under very low energy and cost budgets. The Reconfigurable Streaming Vector Processing (RSVP/spl trade/) is a vector coprocessor architecture which accelerates streaming data processing. This paper presents the RSVP architecture, programming model, and a first implementation. Our results show significant speedups on data streaming functions. Running compiled code, RSVP outperforms an ARM9 host processor on average by a factor of 31 on a set of kernels. From a performance/$ and performance/mW perspective, RSVP 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/spl trade/: an automotive vector processor","authors":"S. Chiricescu, M. Schuette, R. Essick, B. Lucas, P. May, K. Moat, J. Norris","doi":"10.1109/IVS.2004.1336381","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336381","url":null,"abstract":"A myriad of sensors (i.e., video, radar, laser, ultrasound, etc.) continuously monitoring the environment are incorporated in future automobiles. The algorithms processing the data captured by these sensors are streaming in nature and require high levels of processing power. Due to the characteristics of the automotive market, this processing power has to be delivered under very low energy and cost budgets. The Reconfigurable Streaming Vector Processing (RSVP/spl trade/) is a vector coprocessor architecture which accelerates streaming data processing. This paper presents the RSVP architecture, programming model, and a first implementation. Our results show significant speedups on data streaming functions. Running compiled code, RSVP outperforms an ARM9 host processor on average by a factor of 31 on a set of kernels. From a performance/$ and performance/mW perspective, RSVP 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":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":"130567132","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.2004.1336477
P. Jeong, S. Nedvschi, M. Daniliuc
This paper proposes a new approach to detect the driving region and to detect the driving possible region from image sequence. To achieve this, we use local adaptive threshold and local probability for detecting the driving region and for detecting the driving possible region, respectively. Here are the three main aspects. The first one is the driving region detection. For this we use the local adaptive threshold. The second one is to recognize the driving possible region. To do this, we use a randomly selected initial seed and its extension using the distance between local probabilities. The third one is to combine the driving and the driving possible regions. It gives better results for safe autonomous driving. Sometimes, the driving region is not detected correctly due to very great noise factors. In this case the possible driving region still helps autonomous driving.
{"title":"Local probability based safe region detection for autonomous driving","authors":"P. Jeong, S. Nedvschi, M. Daniliuc","doi":"10.1109/IVS.2004.1336477","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336477","url":null,"abstract":"This paper proposes a new approach to detect the driving region and to detect the driving possible region from image sequence. To achieve this, we use local adaptive threshold and local probability for detecting the driving region and for detecting the driving possible region, respectively. Here are the three main aspects. The first one is the driving region detection. For this we use the local adaptive threshold. The second one is to recognize the driving possible region. To do this, we use a randomly selected initial seed and its extension using the distance between local probabilities. The third one is to combine the driving and the driving possible regions. It gives better results for safe autonomous driving. Sometimes, the driving region is not detected correctly due to very great noise factors. In this case the possible driving region still helps autonomous driving.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"383 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":"132170594","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.2004.1336487
K. Fuerstenberg, K. Dietmayer
This paper summarises new approaches combining distance and reflectivity measurements of laser scanners in order to track and classify more accurately. Additionally a new method is introduced, which analyses the motion of the legs of a pedestrian, in order to distinguish between moving pedestrians and balls or boxes in motion. A first estimation of the motion of the pedestrians legs is performed just one second after the first detection. The analysis is widely independent of the pedestrians' distance and direction of motion.
{"title":"Object tracking and classification for multiple active safety and comfort applications using a multilayer laser scanner","authors":"K. Fuerstenberg, K. Dietmayer","doi":"10.1109/IVS.2004.1336487","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336487","url":null,"abstract":"This paper summarises new approaches combining distance and reflectivity measurements of laser scanners in order to track and classify more accurately. Additionally a new method is introduced, which analyses the motion of the legs of a pedestrian, in order to distinguish between moving pedestrians and balls or boxes in motion. A first estimation of the motion of the pedestrians legs is performed just one second after the first detection. The analysis is widely independent of the pedestrians' distance and direction of motion.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"76 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":"126713090","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.2004.1336417
Z. Eizad, Lj. Vlacic
This paper presents a vehicle distance and tracking control system designed for stop-and-go situations. It describes the control scheme in detail and presents results of experimentation conducted to test the control system. This paper also briefly describes a vehicle longitudinal model designed for stop-and-go situations. In the end conclusions are drawn.
{"title":"A control algorithm and vehicle model for stop & go cruise control","authors":"Z. Eizad, Lj. Vlacic","doi":"10.1109/IVS.2004.1336417","DOIUrl":"https://doi.org/10.1109/IVS.2004.1336417","url":null,"abstract":"This paper presents a vehicle distance and tracking control system designed for stop-and-go situations. It describes the control scheme in detail and presents results of experimentation conducted to test the control system. This paper also briefly describes a vehicle longitudinal model designed for stop-and-go situations. In the end conclusions are drawn.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"149 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122343101","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：