Joint Parameter Estimation and Trajectory Tracking of Bounding Boxes
- In multi-extended object tracking, parameters (e.g., extent) and trajectory are often determined independently. In this paper, we propose a joint parameter and trajectory (JPT) state and its integration into the Bayesian framework. This allows processing measurements that contain information about parameters and states. Examples of such measurements are bounding boxes given from an image processing algorithm. It is shown that this approach can consider correlations between states and parameters. In this paper, we present the JPT Bernoulli filter. Since parameters and state elements are considered in the weighting of the measurement data assignment hypotheses, the performance is higher than with the conventional Bernoulli filter. The JPT approach can be also used for other Bayes filters.
Author: | Patrick HoherORCiD, Johannes ReuterORCiD, Felix GovaersORCiD, Wolfgang Koch |
---|---|
URL: | https://ieeexplore.ieee.org/document/9626855 |
ISBN: | 978-1-7377497-1-4 |
Parent Title (English): | 24rd International Conference on Information Fusion (FUSION), 1-4 Nov 2021, Sun City Convention Centre Rustenburg, South Africa |
Publisher: | IEEE |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2021 |
Release Date: | 2022/01/17 |
Tag: | Multi extended object tracking; Bernoulli filter; Sets of trajectories; Bounding boxes |
Page Number: | 8 |
Note: | Volltextzugriff für Angehörige der Hochschule Konstanz via Datenbank IEEE Xplore möglich |
Institutes: | Institut für Systemdynamik - ISD |
Relevance: | Keine peer reviewed Publikation (Wissenschaftlicher Artikel und Aufsatz, Proceeding, Artikel in Tagungsband) |
Open Access?: | Nein |
Licence (German): | Urheberrechtlich geschützt |