Pub Date : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8964988
Quentin Delooz, Andreas Festag
Collective perception uses V2X communications to increase the perception capabilities of vehicles. Relying on the perceived data from their local sensors, nodes exchange information about the objects they detect in their surroundings. An object can be anything significant for the nodes' safety, e.g., obstacles on the road, other vehicles or pedestrians. The amount of data generated by each node is determined by the number of perceived objects and the generation frequency of the messages carrying the detected objects. Considering the limited bandwidth of the wireless channel, the data load generated by collective perception can easily exceed the channel capacity. In this paper, we investigate three schemes that filter the number of objects in the messages and thereby adjust the network load in order to optimize the transmission of perceived objects. Our simulation-based performance evaluation indicates that the use of filtering is an effective approach to improve network-related performance metrics, whereas the expected impairment of the perception quality is rather small. The comparison of the filtering algorithms provide insights into the tradeoff between network-related metrics and perception quality.
{"title":"Network Load Adaptation for Collective Perception in V2X Communications","authors":"Quentin Delooz, Andreas Festag","doi":"10.1109/ICCVE45908.2019.8964988","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8964988","url":null,"abstract":"Collective perception uses V2X communications to increase the perception capabilities of vehicles. Relying on the perceived data from their local sensors, nodes exchange information about the objects they detect in their surroundings. An object can be anything significant for the nodes' safety, e.g., obstacles on the road, other vehicles or pedestrians. The amount of data generated by each node is determined by the number of perceived objects and the generation frequency of the messages carrying the detected objects. Considering the limited bandwidth of the wireless channel, the data load generated by collective perception can easily exceed the channel capacity. In this paper, we investigate three schemes that filter the number of objects in the messages and thereby adjust the network load in order to optimize the transmission of perceived objects. Our simulation-based performance evaluation indicates that the use of filtering is an effective approach to improve network-related performance metrics, whereas the expected impairment of the perception quality is rather small. The comparison of the filtering algorithms provide insights into the tradeoff between network-related metrics and perception quality.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127152287","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965234
V. Jiménez, C. Schwarzl, Helmut Martin
Although indoor localization has been a wide researched topic, obtained results may not fit the requirements that some domains need. Most approaches are not able to precisely localize a fast moving object even with a complex installation, which makes their implementation in the automated driving domain complicated. In this publication, common technologies were analyzed and a commercial product, called Marvelmind Indoor GPS, was chosen for our use case in which both ultrasound and radio frequency communications are used. The evaluation is given in a first moment on small indoor scenarios with static and moving objects. Further tests were done on wider areas, where the system is integrated within our Robotics Operating System (ROS)-based self-developed “Smart PhysIcal Demonstration and evaluation Robot (SPIDER)” and the results of these outdoor tests are compared with the obtained localization by the installed GPS on the robot. Finally, the next steps to improve the results in further developments are discussed.
{"title":"Evaluation of an indoor localization system for a mobile robot","authors":"V. Jiménez, C. Schwarzl, Helmut Martin","doi":"10.1109/ICCVE45908.2019.8965234","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965234","url":null,"abstract":"Although indoor localization has been a wide researched topic, obtained results may not fit the requirements that some domains need. Most approaches are not able to precisely localize a fast moving object even with a complex installation, which makes their implementation in the automated driving domain complicated. In this publication, common technologies were analyzed and a commercial product, called Marvelmind Indoor GPS, was chosen for our use case in which both ultrasound and radio frequency communications are used. The evaluation is given in a first moment on small indoor scenarios with static and moving objects. Further tests were done on wider areas, where the system is integrated within our Robotics Operating System (ROS)-based self-developed “Smart PhysIcal Demonstration and evaluation Robot (SPIDER)” and the results of these outdoor tests are compared with the obtained localization by the installed GPS on the robot. Finally, the next steps to improve the results in further developments are discussed.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114597222","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8964914
Ch. Pilz, Gerald Steinbauer, Markus Schratter, D. Watzenig
Automotive industry is currently shifting from automated driving assistance systems to conditionally automated vehicles. Traditional automotive component testing methodologies are not sufficient to verify these increasingly complex systems. While previous research deals primarily with elementary components of complex verification systems for autonomous driving, commercial software companies combine them without making the results publicly available. The focus of the presented in this paper is to analyze the components necessary to design and build a simulation-based autonomous driving verification system. The results of this analysis are then integrated into a proof-of-concept system whose performance is compared with requirements collected beforehand. The outcome of this work will provide a scientific basis for future developments of autonomous driving verification systems for automotive appliances based on simulation.
{"title":"Development of a Scenario Simulation Platform to Support Autonomous Driving Verification","authors":"Ch. Pilz, Gerald Steinbauer, Markus Schratter, D. Watzenig","doi":"10.1109/ICCVE45908.2019.8964914","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8964914","url":null,"abstract":"Automotive industry is currently shifting from automated driving assistance systems to conditionally automated vehicles. Traditional automotive component testing methodologies are not sufficient to verify these increasingly complex systems. While previous research deals primarily with elementary components of complex verification systems for autonomous driving, commercial software companies combine them without making the results publicly available. The focus of the presented in this paper is to analyze the components necessary to design and build a simulation-based autonomous driving verification system. The results of this analysis are then integrated into a proof-of-concept system whose performance is compared with requirements collected beforehand. The outcome of this work will provide a scientific basis for future developments of autonomous driving verification systems for automotive appliances based on simulation.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123028972","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965238
Johannes Betz, A. Wischnewski, Alexander Heilmeier, Felix Nobis, Leonhard Hermansdorfer, Tim Stahl, T. Herrmann, M. Lienkamp
Based on a software architecture for autonomous driving presented and tested in an autonomous level-5 race-car in 2018 this paper describes in detail the evolutionary enhancement of this software architecture. The architecture combines the autonomous software layers perception, planning and control, which were modularized in the core software. The focus of this paper is the detailed description of how we enhanced the software with a module for an object list creation, a module for the behavioral planning and a module for the creation of dynamic trajectories. These enhancements allow the car to overtake other cars and static obstacles autonomously when driving on the race track. Furthermore, we present with a high novelty value the software module for a vehicle performance maximization, which consists of a control performance assessment and a friction estimation. The software architecture displayed in this paper will be tested and evaluated in the Roborace Season Alpha in 2019.
{"title":"A Software Architecture for the Dynamic Path Planning of an Autonomous Racecar at the Limits of Handling","authors":"Johannes Betz, A. Wischnewski, Alexander Heilmeier, Felix Nobis, Leonhard Hermansdorfer, Tim Stahl, T. Herrmann, M. Lienkamp","doi":"10.1109/ICCVE45908.2019.8965238","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965238","url":null,"abstract":"Based on a software architecture for autonomous driving presented and tested in an autonomous level-5 race-car in 2018 this paper describes in detail the evolutionary enhancement of this software architecture. The architecture combines the autonomous software layers perception, planning and control, which were modularized in the core software. The focus of this paper is the detailed description of how we enhanced the software with a module for an object list creation, a module for the behavioral planning and a module for the creation of dynamic trajectories. These enhancements allow the car to overtake other cars and static obstacles autonomously when driving on the race track. Furthermore, we present with a high novelty value the software module for a vehicle performance maximization, which consists of a control performance assessment and a friction estimation. The software architecture displayed in this paper will be tested and evaluated in the Roborace Season Alpha in 2019.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124553111","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8964864
Konstantin Riedl, Thomas Einmüller, Andreas Noll, Andreas Allgayer, D. Reitze, M. Lienkamp
We present a novel approach for a cloud-based ride-height control for vehicles equipped with an air suspension. The objective of this approach is to improve both efficiency and comfort, especially on single obstacles, by including vehicle-to-vehicle or vehicle-to-infrastructure (V2X) information on the road ahead in the control algorithm. The focus of this paper is the methodology of data processing on a cloud backend and includes three steps: pre-processing, clustering and allocation of streets to the clusters. In the first step, the database is reduced to obstacles relevant for driving comfort. The second step is to find clusters with a high density of obstacles on a road condition map. Finally, the probability of hitting an obstacle is calculated for each road in the area of a cluster, taking the characteristics and the topology of the road network into account. Example data is used to proof the functionality of the method. The proposed method seems to be a suitable approach for big data applications and might improve a vehicle ride-height control with regard to comfort and efficiency.
{"title":"Cloud-Based Vehicle Ride-Height Control","authors":"Konstantin Riedl, Thomas Einmüller, Andreas Noll, Andreas Allgayer, D. Reitze, M. Lienkamp","doi":"10.1109/ICCVE45908.2019.8964864","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8964864","url":null,"abstract":"We present a novel approach for a cloud-based ride-height control for vehicles equipped with an air suspension. The objective of this approach is to improve both efficiency and comfort, especially on single obstacles, by including vehicle-to-vehicle or vehicle-to-infrastructure (V2X) information on the road ahead in the control algorithm. The focus of this paper is the methodology of data processing on a cloud backend and includes three steps: pre-processing, clustering and allocation of streets to the clusters. In the first step, the database is reduced to obstacles relevant for driving comfort. The second step is to find clusters with a high density of obstacles on a road condition map. Finally, the probability of hitting an obstacle is calculated for each road in the area of a cluster, taking the characteristics and the topology of the road network into account. Example data is used to proof the functionality of the method. The proposed method seems to be a suitable approach for big data applications and might improve a vehicle ride-height control with regard to comfort and efficiency.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125991248","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965086
Z. Szalay, Mátyás Szalai, B. Tóth, T. Tettamanti, V. Tihanyi
The paper presents a novel simulation concept for autonomous and highly automated road vehicles, called Scenario-in-the-Loop (SciL) testing. SciL can contribute to a more efficient development, testing and validation of driverless cars, which is a pressing question of our days. SciL based testing introduces a new approach capable to simulate and control realistic traffic scenarios around the autonomous vehicle under test realizing a Digital Twin technology for testing. For realistic traffic generation a high fidelity microscopic traffic simulator (SUMO) and for visualization the Unity 3D game engine are involved. The proposed testing methodology was proved with a real world autonomous car. As a test environment for SciL demonstration ZalaZONE Smart City Zone was used. Two different traffic scenarios (platooning and valet parking with pedestrian dummy) have been successfully tested and demonstrated.
{"title":"Proof of concept for Scenario-in-the-Loop (SciL) testing for autonomous vehicle technology","authors":"Z. Szalay, Mátyás Szalai, B. Tóth, T. Tettamanti, V. Tihanyi","doi":"10.1109/ICCVE45908.2019.8965086","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965086","url":null,"abstract":"The paper presents a novel simulation concept for autonomous and highly automated road vehicles, called Scenario-in-the-Loop (SciL) testing. SciL can contribute to a more efficient development, testing and validation of driverless cars, which is a pressing question of our days. SciL based testing introduces a new approach capable to simulate and control realistic traffic scenarios around the autonomous vehicle under test realizing a Digital Twin technology for testing. For realistic traffic generation a high fidelity microscopic traffic simulator (SUMO) and for visualization the Unity 3D game engine are involved. The proposed testing methodology was proved with a real world autonomous car. As a test environment for SciL demonstration ZalaZONE Smart City Zone was used. Two different traffic scenarios (platooning and valet parking with pedestrian dummy) have been successfully tested and demonstrated.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126063248","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965112
Stephanie Grubmüller, G. Stettinger, M. Sotelo, D. Watzenig
Autonomous vehicles gain more and more attention. Moving towards highly automated vehicles requires the implementation of fault-tolerant systems. In this paper we propose an architecture for a fault-tolerant environmental perception, where either one fault in the hardware or one in the software can be detected. The hardware fault detection relies on a Landmark (LM) tracking approach. The software fault detection is based on comparing the outputs of redundant programs. The faulty module is then excluded in the data fusion algorithm by a fault masking. The functionality of the proposed approach is tested in simulation via injecting one hardware and one software fault.
{"title":"Fault-tolerant environmental perception architecture for robust automated driving","authors":"Stephanie Grubmüller, G. Stettinger, M. Sotelo, D. Watzenig","doi":"10.1109/ICCVE45908.2019.8965112","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965112","url":null,"abstract":"Autonomous vehicles gain more and more attention. Moving towards highly automated vehicles requires the implementation of fault-tolerant systems. In this paper we propose an architecture for a fault-tolerant environmental perception, where either one fault in the hardware or one in the software can be detected. The hardware fault detection relies on a Landmark (LM) tracking approach. The software fault detection is based on comparing the outputs of redundant programs. The faulty module is then excluded in the data fusion algorithm by a fault masking. The functionality of the proposed approach is tested in simulation via injecting one hardware and one software fault.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"1 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122587203","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965161
Bruno Vieira, Ricardo Severino, E. Filho, A. Koubâa, E. Tovar
Safety-critical cooperative vehicle applications such as platooning, require extensive testing, however, the complexity and cost involved in this process, increasingly demands for realistic simulation tools to ease the validation of such technologies, helping to bridge the gap between development and real-word deployment. In this paper we propose a realistic co-simulation framework for cooperative vehicles, that integrates Gazebo, an advanced robotics simulator, with the OMNeT++ network simulator, over the Robot Operating System (ROS) framework, supporting the simulation of advanced cooperative applications such as platooning, in realistic scenarios.
{"title":"COPADRIVe - A Realistic Simulation Framework for Cooperative Autonomous Driving Applications","authors":"Bruno Vieira, Ricardo Severino, E. Filho, A. Koubâa, E. Tovar","doi":"10.1109/ICCVE45908.2019.8965161","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965161","url":null,"abstract":"Safety-critical cooperative vehicle applications such as platooning, require extensive testing, however, the complexity and cost involved in this process, increasingly demands for realistic simulation tools to ease the validation of such technologies, helping to bridge the gap between development and real-word deployment. In this paper we propose a realistic co-simulation framework for cooperative vehicles, that integrates Gazebo, an advanced robotics simulator, with the OMNeT++ network simulator, over the Robot Operating System (ROS) framework, supporting the simulation of advanced cooperative applications such as platooning, in realistic scenarios.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126506204","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965233
Kmeid Saad, Stefan-Alexander Schneider
In this paper, we describe a new approach for synthetic image augmentation and its advantages in training Deep Neural Networks (DNNs) for object classification and localization. To address the need for a significant amount of data when training DNNs, for image-based ADAS functions, our method relies on virtually generated scenarios augmented via a physics-based camera model. The camera model implements various optical effects on ideal-synthetic images. For the scope of this paper, we illustrate the performance differences associated with the vignetting effect when training DNNs with and without image augmentation. We show that training on images altered by our camera vignetting model yield to a better performance than using ideal-synthetic images, additionally we illustrate the relationship between the network's performance results and the implemented effect (vignetting in this case). For a start, our results open the possibility for using camera models for training neural networks on synthetic data and pave the way toward further investigations on significant optical and image sensor effects to be modeled/implemented for performance enhancement during the training process. The approach is conducted and evaluated by training a DNN for car detection using the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) and Virtual KITTI (VKITTI) datasets.
{"title":"Camera Vignetting Model and its Effects on Deep Neural Networks for Object Detection","authors":"Kmeid Saad, Stefan-Alexander Schneider","doi":"10.1109/ICCVE45908.2019.8965233","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965233","url":null,"abstract":"In this paper, we describe a new approach for synthetic image augmentation and its advantages in training Deep Neural Networks (DNNs) for object classification and localization. To address the need for a significant amount of data when training DNNs, for image-based ADAS functions, our method relies on virtually generated scenarios augmented via a physics-based camera model. The camera model implements various optical effects on ideal-synthetic images. For the scope of this paper, we illustrate the performance differences associated with the vignetting effect when training DNNs with and without image augmentation. We show that training on images altered by our camera vignetting model yield to a better performance than using ideal-synthetic images, additionally we illustrate the relationship between the network's performance results and the implemented effect (vignetting in this case). For a start, our results open the possibility for using camera models for training neural networks on synthetic data and pave the way toward further investigations on significant optical and image sensor effects to be modeled/implemented for performance enhancement during the training process. The approach is conducted and evaluated by training a DNN for car detection using the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) and Virtual KITTI (VKITTI) datasets.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129815424","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 : 2019-11-01DOI: 10.1109/ICCVE45908.2019.8965230
Kai Cordes, Norman Nolte, N. Meine, Hellward Broszio
Cooperative maneuvers are of high interest within many V2X applications. The implementation of cooperative maneuvers require the accurate localization of the vehicles. Accurate localizations of the ego-vehicle will be provided by the next generation of connected cars using 5G. Until all cars participate in the network, unconnected cars have to be considered as well. These cars are localized via static cameras positioned next to the road. The scope of this paper is the implementation and evaluation of a system which provides the detection, tracking, and localization of vehicles for a cooperative maneuvers scenario. The application is the lane merge of vehicles where the vehicle localizations are used for the planning of trajectories. The observed vehicles are equipped with GNSS RTK units for their self-localization which is the basis for the accuracy evaluation of the localization provided by the camera system.
{"title":"Accuracy Evaluation of Camera-based Vehicle Localization","authors":"Kai Cordes, Norman Nolte, N. Meine, Hellward Broszio","doi":"10.1109/ICCVE45908.2019.8965230","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965230","url":null,"abstract":"Cooperative maneuvers are of high interest within many V2X applications. The implementation of cooperative maneuvers require the accurate localization of the vehicles. Accurate localizations of the ego-vehicle will be provided by the next generation of connected cars using 5G. Until all cars participate in the network, unconnected cars have to be considered as well. These cars are localized via static cameras positioned next to the road. The scope of this paper is the implementation and evaluation of a system which provides the detection, tracking, and localization of vehicles for a cooperative maneuvers scenario. The application is the lane merge of vehicles where the vehicle localizations are used for the planning of trajectories. The observed vehicles are equipped with GNSS RTK units for their self-localization which is the basis for the accuracy evaluation of the localization provided by the camera system.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132052598","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：