Publisher DOI: 10.1109/ICASSP39728.2021.9414131
Title: Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars
Language: English
Authors: Dubey, Anand 
Santra, Avik 
Fuchs, Jonas 
Lubke, Maximilian 
Weigel, Robert 
Lurz, Fabian 
Keywords: Location awareness, Target tracking, Smoothing methods, Radar tracking, Kalman filters, Vehicle dynamics
Issue Date: Jun-2021
Source: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
Abstract (english): 
Automatic radar based classification of automotive targets, such as pedestrians and cyclist, poses several challenges due to low inter-class variations among different classes and large intra-class variations. Further, different targets required to track in typical automotive scenario can have completely varying dynamics which gets challenging for tracker using conventional state vectors. Compared to state-of-the-art using independent classification and tracking, in this paper, we propose an integrated tracker and classifier leading to a novel Bayesian framework. The tracker’s state vector in the proposed framework not only includes the localization parameters of the targets but is also augmented with the targets’s feature embedding vector. In consequence, the tracker’s performance is optimized due to a better separability of the targets. Furthermore, the classifier’s performance is enhanced due to Bayesian formulation utilizing the temporal smoothing of classifier’s embedding vector.
Conference: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021 
ISBN: 978-1-7281-7605-5
Institute: Hochfrequenztechnik E-3 
Document Type: Chapter/Article (Proceedings)
Peer Reviewed: Yes
Appears in Collections:Publications without fulltext

Show full item record

Page view(s)

Last Week
Last month
checked on Jan 24, 2022

Google ScholarTM


Add Files to Item

Note about this record

Cite this record


Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.