LMB filter based tracking allowing for multiple hypotheses in object reference point association
Beitrag zu einer Konferenz
Authors
Herrmann, Martin
Piroli, Aldi
Strohbeck, Jan
Müller, Johannes
Buchholz, Michael
Faculties
Fakultät für Ingenieurwissenschaften, Informatik und PsychologieInstitutions
Institut für Mess-, Regel- und MikrotechnikPublished in
2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) ; 2020 (2020). - S. 197-203. - ISBN 978-1-7281-6423-6. - eISSN 978-1-7281-6422-9
Link to original publication
https://dx.doi.org/10.1109/MFI49285.2020.9235251Peer review
ja
Document version
acceptedVersion
Conference
2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2020-09-14 - 2020-09-16, Karlsruhe (online only)
Abstract
Autonomous vehicles need precise knowledge on dynamic objects in their surroundings. Especially in urban areas with many objects and possible occlusions, an infrastructure system based on a multi-sensor setup can provide the required environment model for the vehicles. Previously, we have published a concept of object reference points (e.g. the corners of an object), which allows for generic sensor "plug and play" interfaces and relatively cheap sensors. This paper describes a novel method to additionally incorporate multiple hypotheses for fusing the measurements of the object reference points using an extension to the previously presented Labeled Multi-Bernoulli (LMB) filter. In contrast to the previous work, this approach improves the tracking quality in the cases where the correct association of the measurement and the object reference point is unknown. Furthermore, this paper identifies options based on physical models to sort out inconsistent and unfeasible associations at an early stage in order to keep the method computationally tractable for real-time applications. The method is evaluated on simulations as well as on real scenarios. In comparison to comparable methods, the proposed approach shows a considerable performance increase, especially the number of non-continuous tracks is decreased significantly.
Funding information
MEC-View / BMWi [19A16010I]
EU Project
ICT4CART / ICT Infrastructure for Connected and Automated Road Transport / EC / H2020 / 768953
Subject Headings
Autonomes Fahrzeug [GND]Automobile driving--Automation [LCSH]
Keywords
LMB-Filter; Multi-Object TrackingDewey Decimal Group
DDC 620 / Engineering & allied operationsMetadata
Show full item recordCitation example
Herrmann, Martin et al. (2020): LMB filter based tracking allowing for multiple hypotheses in object reference point association. Open Access Repositorium der Universität Ulm. http://dx.doi.org/10.18725/OPARU-33915