Generic Centralized Multi Sensor Data Fusion Based on Probabilistic Sensor and Environment Models for Driver Assistance Systems

Münz, Michael; Mahlisch, Mirko; Dietmayer, Klaus

doi:10.1109/mits.2010.937293

Cited by 48 publications

(40 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The probability theory [53], possibility theory, Dempster-Shafer evidence theory [54], fuzzy set theory, rough set theory and random finite set theory [55,56] are all useful tools to deal with the problem of imperfect or inconsistent data. However, all of these theories have their limitations and are only capable of addressing specific aspects of this issue.…”

Section: Fusion Enginementioning

confidence: 99%

A Review of Multimodal Interaction

Liang¹,

Liang²,

Xue-qian³

et al. 2016

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract-Due to the contribution to a more natural and efficient human-computer interaction style, multimodal interactive systems are becoming more and more commonplace and cover a wide range of applicants. Therefore, there seems to be an urgent need for an introduction to related concepts of multimodal interaction and an analytical review of the-state-of-the-art. In this paper, we try to present a brief review of some of the significant aspects in multimodal interaction. At first, the definition and advantages of multimodal systems are discussed, and then a brief development history of multimodal interaction is introduced. Next, we touch on the recent development in the breadth of work on input/output modalities and fusion engine. Finally, we provide a personal outlook for the research of multimodal interaction. It is our hope for this paper to provide a picture of the contemporary state of multimodal interaction research and a meaningful outlook for this research field.

show abstract

Section: Fusion Enginementioning

confidence: 99%

A Review of Multimodal Interaction

Liang¹,

Liang²,

Xue-qian³

et al. 2016

Advances in Computer Science Research

View full text Add to dashboard Cite

show abstract

“…For this purpose the concept of Dempster-Shafer theory of evidence (DST) based multi-sensor fusion [MMD10] is enhanced. Furthermore, at an intersection in general multiple relevant objects of different type and with different type dependent motion characteristics are present, e.g.…”

Section: ; Ptsmentioning

confidence: 99%

“…A similar approach which uses DST to represent the sensors' recognition ability in a JIPDA framework has been presented in [MMD10]. Consequently, the integration of the object classification in the GM-CMMPHD filter facilitates an adaption of the sensors' detection probability for objects with class BBA m C by:…”

Section: Fusing Sensors With Different Recognition Abilitiesmentioning

confidence: 99%

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Meißner

Reuter

Strigel

et al. 2014

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Bibliografische Information der Deutschen NationalbibliothekDie Deutsche Nationalbibliothek verzeichnet diese Publikation in der Deutschen Nationalbibliografie; detaillierte bibliografische Daten sind im Internet über http://dnb.dnb.de abrufbar. AbstractDue to an increasing number of traffic accident fatalities at intersections, the prevention of traffic accidents at intersection attracts more and more attention in public as well as in research. One example therefore, is the joint-project Ko-PER of the research initiative Ko-FAS which aims to increase the preventive traffic safety. This is realized by an preferably exhaustive recognition of the vehicles' environments based on locally gathered and communicated perception data. Therefore, especially at urban intersections, an intersection-based perception system which communicates the current traffic situation to vehicles in the intersection's surrounding is essential. Thus, a busy public intersection in Aschaffenburg, Germany was equipped with an intersection perception system, which contains multiple laserscanners and video cameras as well as data processing units. Beside the planning of the perception system, the core of this thesis is the laserscanner-based detection and classification of road users and the tracking of them by fusing detections of the laserscanners and video cameras.Since the laserscanners at the intersection are mounted at posts of lamps, traffic-lights as well as surrounding buildings, segmentation algorithms are introduced which utilize the knowledge about the consistent environment to segment the laserscanner measurements in background and foreground. Subsequently, the object detection in the foreground data relies on position as well as motion information. The 3D measurement points are clustered with a real-time capable implementation of the density based spatial clustering for applications with noise (DBSCAN) algorithm. Nevertheless, particularly large objects are sometimes not entirely detected due to occlusions, poor reflection characteristics and measurement uncertainties. This may lead to the separation of one object in multiple clusters. To avoid the overclustering, a combination of 2D tracking and 3D clustering methods is proposed. Beside the benefit of the considerably more robust object detection, additionally the determination of the objects' orientations is improved. Finally, the detected objects are classified by means of features of their laserscanner point clusters.The focus of this thesis lays on the tracking of road users at traffic intersections. Thus, a tracking approach is required which is able to handle multiple objects detected by multiple classifying sensors with different field of views. Due to the topdown modeling of the multi-object tracking problem and the availability of efficient implementations, a Gaussian mixture probability hypothesis density (GM-PHD) filter is used. Based on this the classifying multiple-model probability hypothesis density (CMMPHD) filter is developed which facilitates to track road user...

show abstract

“…However, in some battlefield environment of harshness or severe noise, sensor nodes are required to spread in designated areas to detect moving targets, influence such as external environment, sensor type, measurement noise, monitoring location and other factors will affect the supervision accuracy, causing the data collected by sensor network uncertain, untrue and unreliable, as a result, monitoring deviations and errors occur during the supervision process [1]. In order to guarantee the data collection of sensor more reliable, a number of scholars have proposed some multi-sensor data fusion solutions, nevertheless, many of them often lead to unbalanced information among sensor nodes in the process of data fusion.…”

Section: Introductionmentioning

confidence: 99%