The Experts below are selected from a list of 561 Experts worldwide ranked by ideXlab platform
Uwe Franke - One of the best experts on this subject based on the ideXlab platform.
-
visual Guard rail detection for advanced highway assistance systems
Intelligent Vehicles Symposium, 2014Co-Authors: Timo Scharwachter, Manuela Schuler, Uwe FrankeAbstract:In this paper we present a novel method to detect Guard Rails in highway scenarios using a stereo camera setup. In contrast to previous methods, we combine geometry information with appearance cues using a state-of-the-art feature encoding method. In our system pipeline, we follow a hough-based approach to localize potential Guard Rails in the image and require each detected line to fulfill linearity in depth as well as certain height expectations. To leverage the appearance information, we exploit an efficient bag-of-features representation that relies on randomized clustering forests. The effectiveness of our approach is demonstrated on a large novel dataset with pixel-level annotations of Guard Rails in real-world highway scenarios.
-
Intelligent Vehicles Symposium - Visual Guard rail detection for advanced highway assistance systems
2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014Co-Authors: Timo Scharwachter, Manuela Schuler, Uwe FrankeAbstract:In this paper we present a novel method to detect Guard Rails in highway scenarios using a stereo camera setup. In contrast to previous methods, we combine geometry information with appearance cues using a state-of-the-art feature encoding method. In our system pipeline, we follow a hough-based approach to localize potential Guard Rails in the image and require each detected line to fulfill linearity in depth as well as certain height expectations. To leverage the appearance information, we exploit an efficient bag-of-features representation that relies on randomized clustering forests. The effectiveness of our approach is demonstrated on a large novel dataset with pixel-level annotations of Guard Rails in real-world highway scenarios.
A Gessler - One of the best experts on this subject based on the ideXlab platform.
-
Innovative Schutzplanken aus Stahl / Innovative Steel Safety Guard Rails
2005Co-Authors: G Sedlacek, C Kammel, A GesslerAbstract:Zur Erhoehung der Sicherheit der Verkehrssysteme wurde in Zusammenarbeit mit der Industrie eine modular aufgebaute Produktfamilie fuer ein innovatives Fahrzeugrueckhaltesystem aus Stahl entwickelt, das gleichzeitig eine optimale Schutzwirkung, Nachhaltigkeit und Multifunktionalitaet gewaehrleistet und je nach Schutzanforderung und Einsatzzweck zusammengesetzt werden kann. Beitraege zur Entwicklung lieferten der Lehrstuhl fuer Stahlbau der RWTH Aachen, der sich mit der konstruktiven Gestaltung des Rueckhaltesystems und der Vorhersage der Anprallpruefungsergebnisse befasste, das Institut fuer Eisenhuettenkunde der RWTH Aachen, das die Eignung von neuartigen, kontinuierlich beschichteten Planken fuer einen ausreichenden Korrosionsschutz in Laborversuchen nachwies und das Fraunhofer-Institut fuer Lasertechnik Aachen, das innovative Loesungen fuer einen dauerhaften Schnittkantenschutz der Planken entwickelte. ABSTRACT IN ENGLISH: To increase road safety a modular structured product family of an innovative road restraint system made of steel was developed in cooperation with the industry, providing for high level of protection, sustainability and multi-functionality coinstantaneously, that can be composed depending on intended protection and application purposes. Contributions to the development were delivered by the Institute of Steel Construction of the RWTH Aachen, which dealt with the constructive aspects of the road restraint system and with the prediction of impact test results, by the Institute of Iron Making and Metallurgy of the RWTH Aachen, proving the fitness for use for novel, continuously coated structural steel strip products with regard to corrosion protection and by the Fraunhofer Institute for Laser Technology Aachen, developing innovative coating solutions for a permanent corrosion protection of the strip cutting area. (A)
-
innovative schutzplanken aus stahl innovative steel safety Guard Rails
Strassenverkehrstechnik, 2005Co-Authors: G Sedlacek, C Kammel, A GesslerAbstract:Zur Erhoehung der Sicherheit der Verkehrssysteme wurde in Zusammenarbeit mit der Industrie eine modular aufgebaute Produktfamilie fuer ein innovatives Fahrzeugrueckhaltesystem aus Stahl entwickelt, das gleichzeitig eine optimale Schutzwirkung, Nachhaltigkeit und Multifunktionalitaet gewaehrleistet und je nach Schutzanforderung und Einsatzzweck zusammengesetzt werden kann. Beitraege zur Entwicklung lieferten der Lehrstuhl fuer Stahlbau der RWTH Aachen, der sich mit der konstruktiven Gestaltung des Rueckhaltesystems und der Vorhersage der Anprallpruefungsergebnisse befasste, das Institut fuer Eisenhuettenkunde der RWTH Aachen, das die Eignung von neuartigen, kontinuierlich beschichteten Planken fuer einen ausreichenden Korrosionsschutz in Laborversuchen nachwies und das Fraunhofer-Institut fuer Lasertechnik Aachen, das innovative Loesungen fuer einen dauerhaften Schnittkantenschutz der Planken entwickelte. ABSTRACT IN ENGLISH: To increase road safety a modular structured product family of an innovative road restraint system made of steel was developed in cooperation with the industry, providing for high level of protection, sustainability and multi-functionality coinstantaneously, that can be composed depending on intended protection and application purposes. Contributions to the development were delivered by the Institute of Steel Construction of the RWTH Aachen, which dealt with the constructive aspects of the road restraint system and with the prediction of impact test results, by the Institute of Iron Making and Metallurgy of the RWTH Aachen, proving the fitness for use for novel, continuously coated structural steel strip products with regard to corrosion protection and by the Fraunhofer Institute for Laser Technology Aachen, developing innovative coating solutions for a permanent corrosion protection of the strip cutting area. (A)
Timo Scharwachter - One of the best experts on this subject based on the ideXlab platform.
-
visual Guard rail detection for advanced highway assistance systems
Intelligent Vehicles Symposium, 2014Co-Authors: Timo Scharwachter, Manuela Schuler, Uwe FrankeAbstract:In this paper we present a novel method to detect Guard Rails in highway scenarios using a stereo camera setup. In contrast to previous methods, we combine geometry information with appearance cues using a state-of-the-art feature encoding method. In our system pipeline, we follow a hough-based approach to localize potential Guard Rails in the image and require each detected line to fulfill linearity in depth as well as certain height expectations. To leverage the appearance information, we exploit an efficient bag-of-features representation that relies on randomized clustering forests. The effectiveness of our approach is demonstrated on a large novel dataset with pixel-level annotations of Guard Rails in real-world highway scenarios.
-
Intelligent Vehicles Symposium - Visual Guard rail detection for advanced highway assistance systems
2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014Co-Authors: Timo Scharwachter, Manuela Schuler, Uwe FrankeAbstract:In this paper we present a novel method to detect Guard Rails in highway scenarios using a stereo camera setup. In contrast to previous methods, we combine geometry information with appearance cues using a state-of-the-art feature encoding method. In our system pipeline, we follow a hough-based approach to localize potential Guard Rails in the image and require each detected line to fulfill linearity in depth as well as certain height expectations. To leverage the appearance information, we exploit an efficient bag-of-features representation that relies on randomized clustering forests. The effectiveness of our approach is demonstrated on a large novel dataset with pixel-level annotations of Guard Rails in real-world highway scenarios.
Christian Lundquist - One of the best experts on this subject based on the ideXlab platform.
-
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-62849 RANDOM SET BASED ROAD MAPPING USING RADAR MEASUREMENTS
2013Co-Authors: Christian Lundquist, Fredrik Gustafsson, Lars Danielsson, Om Set Based RoadAbstract:This work is concerned with the problem of multi-sensor multitarget tracking of stationary road side objects, i.e. Guard Rails and parked vehicles, in the context of automotive active safety systems. Advanced active safety applications, such as collision avoidance by steering, rely on obtaining a detailed map of the surrounding infrastructure to accurately assess the situation. Here, this map consists of the position of objects, represented by a random finite set (RFS) of multi-target states and we propose to describe the map as the spatial stationary object intensity. This intensity is the first order moment of a multi-target RFS representing the position of stationary objects and it is calculated using a Gaussian mixture probability hypothesis density (GM-PHD) filter. 1
-
EUSIPCO - Random set based road mapping using radar measurements
2010Co-Authors: Christian Lundquist, Lars Danielssorf, Fredrik GustafssorAbstract:This work is concerned with the problem of multi-sensor multitarget tracking of stationary road side objects, i.e. Guard Rails and parked vehicles, in the context of automotive active safety systems. Advanced active safety applications, such as collision avoidance by steering, rely on obtaining a detailed map of the surrounding infrastructure to accurately assess the situation. Here, this map consists of the position of objects, represented by a random finite set (RFS) of multi-target states and we propose to describe the map as the spatial stationary object intensity. This intensity is the first order moment of a multi-target RFS representing the position of stationary objects and it is calculated using a Gaussian mixture probability hypothesis density (GM-PHD) filter.
-
FUSION - Estimating polynomial structures from radar data
2010 13th International Conference on Information Fusion, 2010Co-Authors: Christian Lundquist, Umut Orguner, Fredrik GustafssonAbstract:Situation awareness for vehicular safety and autonomy functions includes knowledge of the drivable area. This area is normally constrained between stationary road-side objects as Guard-Rails, curbs, ditches and vegetation. We consider these as extended objects modeled by polynomials along the road, and propose an algorithm to track each polynomial based on noisy range and bearing detections, typically from a radar. A straightforward Kalman filter formulation of the problem suffers from the errors-in-variables (EIV) problem in that the noise enters the system model. We propose an EIV modification of the Kalman filter and demonstrates its usefulness using radar data from public roads.
-
Tracking stationary extended objects for road mapping using radar measurements
2009 IEEE Intelligent Vehicles Symposium, 2009Co-Authors: Christian Lundquist, Umut Orguner, Thomas B. SchönAbstract:It is getting more common that premium cars are equipped with a forward looking radar and a forward looking camera. The data is often used to estimate the road geometry, tracking leading vehicles, etc. However, there is valuable information present in the radar concerning stationary objects, that is typically not used. The present work shows how stationary objects, such as Guard Rails, can be modeled and tracked as extended objects using radar measurements. The problem is cast within a standard sensor fusion framework utilizing the Kalman filter. The approach has been evaluated on real data from highways and rural roads in Sweden.
Raphael H Grzebieta - One of the best experts on this subject based on the ideXlab platform.
-
motorcycle impacts into roadside barriers real world accident studies crash tests and simulations carried out in germany and australia
Proceedings of the 19th International Technical Conference on the Enhanced Safety of Vehicles (ESV), 2005Co-Authors: Alexander Berg, Peter Rucker, Marcus Gartner, Jens Konig, Raphael H GrzebietaAbstract:Roadside protection systems such as steel Guard Rails or concrete barriers were originally developed to protect occupants of cars and/or trucks – but not to protect impacting motorcycle riders. Motorcycle rider crashes into such barriers have been identified as resulting in severe injuries and hence has become a subject of road safety research. The German Federal Highway Research Institute (BASt) requested DEKRA Accident Research to analyze real-world crashes involving motorcycles impacting roadside barriers and to identify typical crash characteristics for full-scale crash tests of a conventional steel system and a concrete barrier. A study of 57 real-world crashes identified two crash test scenarios which have been carried out: one with the motorcycle driven in an upright position and one with the motorcycle with the rider sliding on the road surface. The pre-crash velocity chosen was 60 km/h. The impact angle was 12° for the upright driven motorcycle and 25° for the motorcycle and rider sliding. Two crash tests have been conducted to analyze impacts onto conventional steel Guard Rails and two tests to analyze impacts onto a concrete barrier. Two additional full-scale crash tests were carried out to analyze the behavior of a modified roadside protection system made from steel. A second phase of the work involved carrying out computer simulations at Monash University?s Department of Civil Engineering. The DEKRA results from the crash test, where the upright motorcycle impacts the concrete barrier, were used to validate a MADYMO motorcycle-barrier model. This model was then used to investigate other impact speeds, a 25° impact angle scenario and different impact scenarios between an upright motorcycle and a wire rope barrier system. The results revealed that the risk for motorcyclists of being injured when colliding with either a wire rope or a concrete barrier will be high. The paper describes the relevant real-world accident scenarios, the different roadside protection systems used for the tests, the crash tests, the modeling simulations and the results, and proposes improvements to barrier systems to reduce injury severity.
-
Motorcycle Impacts into Roadside Barriers – Real-World Accident Studies, Crash Tests and Simulations Carried Out in Germany and Australia
2005Co-Authors: Alexander Berg, Peter Rucker, Marcus Gartner, Jens Konig, Raphael H Grzebieta, Roger ZouAbstract:Roadside protection systems such as steel Guard Rails or concrete barriers were originally developed to protect occupants of cars and/or trucks – but not to protect impacting motorcycle riders. Motorcycle rider crashes into such barriers have been identified as resulting in severe injuries and hence has become a subject of road safety research. The German Federal Highway Research Institute (BASt) requested DEKRA Accident Research to analyze real-world crashes involving motorcycles impacting roadside barriers and to identify typical crash characteristics for full-scale crash tests of a conventional steel system and a concrete barrier. A study of 57 real-world crashes identified two crash test scenarios which have been carried out: one with the motorcycle driven in an upright position and one with the motorcycle with the rider sliding on the road surface. The pre-crash velocity chosen was 60 km/h. The impact angle was 12° for the upright driven motorcycle and 25° for the motorcycle and rider sliding. Two crash tests have been conducted to analyze impacts onto conventional steel Guard Rails and two tests to analyze impacts onto a concrete barrier. Two additional full-scale crash tests were carried out to analyze the behavior of a modified roadside protection system made from steel. A second phase of the work involved carrying out computer simulations at Monash University?s Department of Civil Engineering. The DEKRA results from the crash test, where the upright motorcycle impacts the concrete barrier, were used to validate a MADYMO motorcycle-barrier model. This model was then used to investigate other impact speeds, a 25° impact angle scenario and different impact scenarios between an upright motorcycle and a wire rope barrier system. The results revealed that the risk for motorcyclists of being injured when colliding with either a wire rope or a concrete barrier will be high. The paper describes the relevant real-world accident scenarios, the different roadside protection systems used for the tests, the crash tests, the modeling simulations and the results, and proposes improvements to barrier systems to reduce injury severity.
