Zur Kurzanzeige

AutorMunz, Michaeldc.contributor.author
Aufnahmedatum2016-03-15T06:22:59Zdc.date.accessioned
In OPARU verfügbar seit2016-03-15T06:22:59Zdc.date.available
Jahr der Erstellung2011dc.date.created
ZusammenfassungThe presented work provides a contribution in the field of automotive environment perception based on sensor fusion systems. In contrast to other existing fusion systems, a generic framework is realized, which allows for exchanging any sensor module without the need to adapt the fusion algorithm. This is achieved by modeling sensor specific properties like detection performance or reliability in a probabilistic way, which allows the definition of abstract interfaces between sensor and fusion module. The fusion process is carried out by simultaneously estimating state and existence of objects based on probabilistic information by the sensors. In addition, the resulting environment model can be processed by different driver assistance applications at the same time, which may have unequal needs for reliability of object existence. The requirements for a generic fusion system are analyzed and the need for novel sensor fusion algorithms is described. Existing data fusion algorithms are extended for the claims of the generic fusion system and novel data fusion methods are introduced. Approximations for handling the computationally expensive calculations in real-time are developed which allow ensuring a maximum computing time of the fusion process. Moreover, methods for modeling sensor specific properties, object birth, and object classification are presented. The proposed sensor fusion system is implemented for a specific sensor combination consisting of a laser scanner and a video camera for detecting and tracking vehicles in dense environments like inner city areas. Practical considerations concerning cross-calibration of sensors and timing aspects are provided. The probabilistic sensor models are described in detail. Finally, an exhaustive evaluation of the system based on real-world data is presented and several algorithms are compared. Relevant system parameters like detection performance, tracking time, estimation consistency and state precision are examined.dc.description.abstract
Sprachededc.language.iso
Verbreitende StelleUniversität Ulmdc.publisher
LizenzStandard (Fassung vom 01.10.2008)dc.rights
Link zum Lizenztexthttps://oparu.uni-ulm.de/xmlui/license_v2dc.rights.uri
SchlagwortEnvironment perceptiondc.subject
SchlagwortExistenzschätzungdc.subject
SchlagwortFahrzeugumfelderfassungdc.subject
SchlagwortInformation fusiondc.subject
SchlagwortInformationsfusiondc.subject
SchlagwortJIPDAdc.subject
SchlagwortJoint Integrated Probabilistic Data Associationdc.subject
SchlagwortMulti target trackingdc.subject
DDC-SachgruppeDDC 620 / Engineering & allied operationsdc.subject.ddc
LCSHDriver assistance systemsdc.subject.lcsh
LCSHSensor fusiondc.subject.lcsh
TitelGenerisches Sensorfusionsframework zur gleichzeitigen Zustands- und Existenzschätzung für die Fahrzeugumfelderkennungdc.title
RessourcentypDissertationdc.type
DOIhttp://dx.doi.org/10.18725/OPARU-1763dc.identifier.doi
PPN34791165Xdc.identifier.ppn
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-vts-77002dc.identifier.urn
GNDFahrerassistenzsystemdc.subject.gnd
FakultätFakultät für Ingenieurwissenschaften und Informatikuulm.affiliationGeneral
Datum der Freischaltung2011-07-15T10:20:39Zuulm.freischaltungVTS
Peer-Reviewneinuulm.peerReview
Signatur DruckexemplarZ: J-H 14.127; W: W-H 12.590uulm.shelfmark
DCMI MedientypTextuulm.typeDCMI
VTS-ID7700uulm.vtsID
KategoriePublikationenuulm.category
Ulmer SchriftenreiheSchriftenreihe des Instituts für Mess-, Regel- und Mikrotechnikuulm.seriesUlmName


Dateien zu dieser Ressource

Thumbnail

Das Dokument erscheint in:

Zur Kurzanzeige