The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
By combining statistical pattern recognition techniques and a classic multiple-model vehicle tracking framework, the presented algorithm improves the performance of fusing GPS outputs and vehicle motion data. The multiple-model tracking framework is used to represent vehicle motion as a combination of several maneuvers, whilst, pattern recognition techniques are proposed to identify the model that...
The estimation of a vehiclepsilas dynamic state is one of the most fundamental data fusion tasks for intelligent traffic applications. For that, motion models are applied in order to increase the accuracy and robustness of the estimation. This paper surveys numerous (especially curvilinear) models and compares their performance using a tracking tasks which includes the fusion of GPS and odometry data...
The challenge of modern sensor systems is besides the tracking of targets more and more their classification. The knowledge of the target class has significant influence on the identification, threat evaluation and weapon assignment process of large systems. Especially, considering new types of threats in anti asymmetric warfare the knowledge of a target class has an important drawback. Also the target...
Vector roadmaps are invaluable for various applications such as navigation and tracking. A new algorithm is presented aimed at incrementally producing exact, up-to-date vector roadmaps using GMTI tracks. In most existing work the track points are processed independently. Track points are individually associated with segments of existing roads and the road segment locations are corrected accordingly...
This paper presents a methodology for multi sensor data fusion that uses the accumulation grid idea for the representation of data. A generalized grid framework is introduced to represent measurement data and fusion results in a common way. This allows the definition of standardized prediction and fusion operations and includes the variation between Cartesian and polar grids as well as the extension...
The aim of this paper is to present a multiple object tracking data fusion technique, which fuses radar, image, and ego vehicle odometry. The data are fused at a high level, which leads to reliable and stable tracking results providing also additional features as width estimation and the detection of stationary objects. A ldquorealrdquo application of these algorithms is illustrated on a specific...
In the scope of the EU funded TRACKSS project on cooperative advanced sensors for road traffic applications, we investigate the potential of pre-existing road traffic sensors for pedestrian crossing detection. Two road traffic video-sensors provide spatial occupancy rates on areas along a crosswalk. We propose to correct pedestrian under-detection with a double fusion process composed of inter-sensor...
The identity management problem is the problem of probabilistically keeping track of the association between target tracks and target identities, based on observations made by sensors. Updates of the belief state can happen because of new sensor observations reflecting on target identity, or because targets come near each other so that their identities become confused or mixed. Since the space of...
Many acoustic factors can contribute to the classification accuracy of ground vehicles. Classification based on Acoustic information fusion for ground vehicle classification a single feature set may lose some useful information. To obtain more complete knowledge regarding vehiclespsila acoustic characteristics, we propose a fusion approach to combine two sets of features, in which various aspects...
This paper considers the problem of the classification of objects observed by vehicle embedded sensors. We propose a general architecture and an algorithm to perform multisensor fusion for the classification purpose. The proposed solution has to be robust and flexible. The robustness is essential because this system is for safety applications. The flexibility is ensured by a modular architecture alongside...
This paper presents a high level fusion approach suitable for automotive sensor networks with redundant field of views. The advantage of this method is that it ensures system modularity and allows benchmarking, as it does not permit feedbacks and loops inside the processing. The proposed algorithm deals with the issue of multidimensional assignment as the test vehicle comprises four forward looking...
We report here on our effort to investigate the types of hard/soft information that can be realistically collected in an urban operational environment and to generate a data set that can be used for the development of hard/soft data fusion algorithms. Specifically, we discuss: 1) sources of ldquohard informationldquo (i.e. information from physics-based sources) and ldquosoft informationrdquo (i.e...
Ground targets are constrained on the Earth with their velocity vector direction aligned mostly along the body longitudinal axis. The pose angle therefore carries kinematic information useful for tracking maneuvering targets. For target identification (ID), range profiles obtained by a high range resolution (HRR) radar are compared with reference templates in pose angle per target class, thus producing...
This paper presents an outdoor geo-localisation method, which integrates several information sources: measurements from GPS, incremental encoders and gyroscope, 2D images provided by an on-board camera and a virtual 3D city model. A 3D cartographical observation of the vehicle pose is constructed. This observation is based on the matching between the acquired 2D images and the virtual 3D city model...
The paper summarizes work to date directed at defining a service-based functional decomposition of the fusion process. The resulting architecture accommodates (1) traditional sensor data, as well as human-generated input, (2) streaming and nonstreaming data, and (3) the fusion of both physical and non-physical entities. Fifteen base level fusion services are identified then utilized to construct a...
In many environments where autonomous air or ground vehicles are used to collect information, there will be a known prioritization of areas of the environment where most valuable information will be found. Over time, priorities may change with areas losing value or suddenly becoming important. In this paper, we present an approach to planning paths for vehicles collecting information in such environments,...
This paper presents a method for the management of information dissemination in a vehicular network (VANET). Due to the particularities of the application (ad hoc network, dynamical nodes, broadcast messages), an algorithm has been developed to fuse and combine data in distributed systems. Matching spatial information is made easier by the use of a numerical map as support of a database. A model of...
In this paper a multi sensor system for so called vulnerable road user recognition is presented, developed within an EU project for road safety improvement. The data fusion concept rests upon the sensors near infrared camera and wireless ranging devices, which are complemetary concerning their physical properties. By means of an object oriented approach using the Kalman Filter the introduced concept...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.