Marcus Baum
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Marcus Baum has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Uwe D. Hanebeck
Intelligent Sensor Actuator-Systems Laboratory, Karlsruhe Institute of Technology, Karlsruhe, Germany
30 shared publications Peter Willett
11 shared publicationsBenjamin Noack
Intelligent Sensor-Actuator-Systems Laboratory (ISAS), Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT), Germany
7 shared publicationsFlorian Faion
Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany
7 shared publicationsAntonio Zea
Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany
6 shared publications- Kolja Thormann
Institute of Computer Science, University of Goettingen
6 shared publications
Latest Publications
- Open Access
- 18 March 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 250
Robust online monitoring of aircraft modal parameters using data fusion-based mode tracking
- 18 March 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 250
Open AccessRobust online monitoring of aircraft modal parameters using data fusion-based mode tracking
- Open Access
Quadratic Kalman Filter for Elliptical Extended Object Tracking based on Decoupling State Components
Extended object tracking involves estimating both the physical extent and kinematic parameters of a target object, where typically multiple measurements are observed per time step. In this article, we propose a deterministic closed-form elliptical extended object tracker, based on decoupling of the kinematics, orientation, and axis lengths. By disregarding potential correlations between these state components, fewer approximations are required for the individual estimators than for an overall joint solution. The resulting algorithm outperforms existing algorithms, reaching the accuracy of sampling-based procedures. Additionally, a batch-based variant is introduced, yielding highly efficient computation while outperforming all comparable state-of-the-art algorithms. This is validated both by a simulation study using common models from literature, as well as an extensive quantitative evaluation on real automotive radar data.
Open AccessQuadratic Kalman Filter for Elliptical Extended Object Tracking based on Decoupling State Components
Extended object tracking involves estimating both the physical extent and kinematic parameters of a target object, where typically multiple measurements are observed per time step. In this article, we propose a deterministic closed-form elliptical extended object tracker, based on decoupling of the kinematics, orientation, and axis lengths. By disregarding potential correlations between these state components, fewer approximations are required for the individual estimators than for an overall joint solution. The resulting algorithm outperforms existing algorithms, reaching the accuracy of sampling-based procedures. Additionally, a batch-based variant is introduced, yielding highly efficient computation while outperforming all comparable state-of-the-art algorithms. This is validated both by a simulation study using common models from literature, as well as an extensive quantitative evaluation on real automotive radar data.
- Open Access
Track-to-Track Association for Collective Perception based on Stochastic Optimization
Collective perception is a key aspect for autonomous driving in smart cities as it aims to combine the local environment models of multiple intelligent vehicles in order to overcome sensor limitations. A crucial part of multi-sensor fusion is track-to-track association. Previous works often suffer from high computational complexity or are based on heuristics. We propose an association algorithms based on stochastic optimization, which leverages a multidimensional likelihood incorporating the number of tracks and their spatial distribution and furthermore computes several association hypotheses. We demonstrate the effectiveness of our approach in Monte Carlo simulations and a realistic collective perception scenario computing high-likelihood associations in ambiguous settings.
Open AccessTrack-to-Track Association for Collective Perception based on Stochastic Optimization
Collective perception is a key aspect for autonomous driving in smart cities as it aims to combine the local environment models of multiple intelligent vehicles in order to overcome sensor limitations. A crucial part of multi-sensor fusion is track-to-track association. Previous works often suffer from high computational complexity or are based on heuristics. We propose an association algorithms based on stochastic optimization, which leverages a multidimensional likelihood incorporating the number of tracks and their spatial distribution and furthermore computes several association hypotheses. We demonstrate the effectiveness of our approach in Monte Carlo simulations and a realistic collective perception scenario computing high-likelihood associations in ambiguous settings.
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 73 (1053587X) , 2590-2602
Extended Object Tracking by Rao-Blackwellized Particle Filtering for Orientation Estimation
Extended object tracking is concerned with estimation of object properties regarding both the kinematics and extent, i.e., shape. Particular challenges arise in case the orientation of the target is varying. Existing algorithms exhibit reduced filtering quality in difficult situations. We develop a particle filter-based elliptical extended object tracker, marginalizing the orientation from the state. Monte Carlo techniques are employed for orientation estimation, and a closed-form quadratic estimator for the semi-axis lengths with given orientation is derived. Laplace’s approximation allows for an efficient closed-form computation of the marginal measurement likelihood. In order to determine a point estimate from a set of particles, the geometrical properties of the extended object state are incorporated. Extensive evaluation is carried out, demonstrating a significant improvement in accuracy compared to state-of-the-art methods. Despite the particle-based nature of the approach, large computational burdens are avoided due to the bounded nature of the sampled (one-dimensional) state.
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 73 (1053587X) , 2590-2602
Extended Object Tracking by Rao-Blackwellized Particle Filtering for Orientation Estimation
Extended object tracking is concerned with estimation of object properties regarding both the kinematics and extent, i.e., shape. Particular challenges arise in case the orientation of the target is varying. Existing algorithms exhibit reduced filtering quality in difficult situations. We develop a particle filter-based elliptical extended object tracker, marginalizing the orientation from the state. Monte Carlo techniques are employed for orientation estimation, and a closed-form quadratic estimator for the semi-axis lengths with given orientation is derived. Laplace’s approximation allows for an efficient closed-form computation of the marginal measurement likelihood. In order to determine a point estimate from a set of particles, the geometrical properties of the extended object state are incorporated. Extensive evaluation is carried out, demonstrating a significant improvement in accuracy compared to state-of-the-art methods. Despite the particle-based nature of the approach, large computational burdens are avoided due to the bounded nature of the sampled (one-dimensional) state.
- 22 May 2025
- Published by Springer Nature
- p. 149-154
A Blimp-Based Robot That Moves Under the Ceiling
- Open Access
- 10 May 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (10) , 2503
An Overview of the PAKF-JPDA Approach for Elliptical Multiple Extended Target Tracking Using High-Resolution Marine Radar Data
Ground radar stations observing specific regions of interest nowadays provide detections in the form of point-clouds. This article focuses on a framework that consists of an elliptical multitarget tracker, referred to as Principal-Axes based Kalman Filter (PAKF)-based Joint Probabilistic Data Association (JPDA) (PAKF-JPDA), to enable maritime traffic monitoring. The framework touches on two major stages, target detection and target tracking. For the former, we employed a clustering approach and for the latter, we presented a data-association-based version of the PAKF tracker with an automatic track management functionality. The framework’s benefits are demonstrated when it is applied to the radar streaming in a harbor setting based on a homogeneous multisensor tracking system by comparing our results against their corresponding reference data with visualizations, including performance measures.
- 10 May 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (10) , 2503
Open AccessAn Overview of the PAKF-JPDA Approach for Elliptical Multiple Extended Target Tracking Using High-Resolution Marine Radar Data
Ground radar stations observing specific regions of interest nowadays provide detections in the form of point-clouds. This article focuses on a framework that consists of an elliptical multitarget tracker, referred to as Principal-Axes based Kalman Filter (PAKF)-based Joint Probabilistic Data Association (JPDA) (PAKF-JPDA), to enable maritime traffic monitoring. The framework touches on two major stages, target detection and target tracking. For the former, we employed a clustering approach and for the latter, we presented a data-association-based version of the PAKF tracker with an automatic track management functionality. The framework’s benefits are demonstrated when it is applied to the radar streaming in a harbor setting based on a homogeneous multisensor tracking system by comparing our results against their corresponding reference data with visualizations, including performance measures.
- Open Access
- 4 August 2022
- Published by Springer Nature in BMC Bioinformatics
- Vol. 23 (1) , 1-6
ImputAccur: fast and user-friendly calculation of genotype-imputation accuracy-measures
Background: ImputAccur is a software tool to measure genotype-imputation accuracy. Imputation of untyped markers is a standard approach in genome-wide association studies to close the gap between directly genotyped and other known DNA variants. However, high accuracy for imputed genotypes is fundamental. Several accuracy measures have been proposed, but unfortunately, they are implemented on different platforms, which is impractical. Results: With ImputAccur, the accuracy measures info, Iam-hiQ and r2-based indices can be derived from standard output files of imputation software. Sample/probe and marker filtering is possible. This allows e.g. accurate marker filtering ahead of data analysis. Conclusions: The source code (Python version 3.9.4), a standalone executive file, and example data for ImputAccur are freely available at https://gitlab.gwdg.de/kolja.thormann1/imputationquality.git.
- 4 August 2022
- Published by Springer Nature in BMC Bioinformatics
- Vol. 23 (1) , 1-6
Open AccessImputAccur: fast and user-friendly calculation of genotype-imputation accuracy-measures
Background: ImputAccur is a software tool to measure genotype-imputation accuracy. Imputation of untyped markers is a standard approach in genome-wide association studies to close the gap between directly genotyped and other known DNA variants. However, high accuracy for imputed genotypes is fundamental. Several accuracy measures have been proposed, but unfortunately, they are implemented on different platforms, which is impractical. Results: With ImputAccur, the accuracy measures info, Iam-hiQ and r2-based indices can be derived from standard output files of imputation software. Sample/probe and marker filtering is possible. This allows e.g. accurate marker filtering ahead of data analysis. Conclusions: The source code (Python version 3.9.4), a standalone executive file, and example data for ImputAccur are freely available at https://gitlab.gwdg.de/kolja.thormann1/imputationquality.git.
- Open Access
ImputAccur: fast and user-friendly calculation of genotype-imputation accuracy-measures
Summary: ImputAccur is a software tool for genotype-imputation accuracy-measures. Imputation of untyped markers is a standard approach in genome-wide association studies to close the gap between directly genotyped and other known DNA variants. However high accuracy for imputed genotypes is fundamental. Several accuracy measures have been proposed, but unfortunately, they are implemented on different platforms, which is impractical. With ImputAccur the accuracy measures info, Iam-hiQ and r²based indices can be derived from standard output-files of imputation software. Sample/probe and marker filtering is possible. This allows e.g. accurate marker filtering ahead of data analysis. A Python code is available but also a stand-alone executable file. Availability and Implementation: The source code (Python version 3.9.4), a stand-alone executive file, and example data for ImputAccur are freely available at https://gitlab.gwdg.de/kolja.thormann1/imputationquality.git . Supplementary Information: Supplementary information is available at Bioinformatics online. Contact: arosenb@gwdg.de or koljaalexander.thormann@uni-goettingen.de
Open AccessImputAccur: fast and user-friendly calculation of genotype-imputation accuracy-measures
Summary: ImputAccur is a software tool for genotype-imputation accuracy-measures. Imputation of untyped markers is a standard approach in genome-wide association studies to close the gap between directly genotyped and other known DNA variants. However high accuracy for imputed genotypes is fundamental. Several accuracy measures have been proposed, but unfortunately, they are implemented on different platforms, which is impractical. With ImputAccur the accuracy measures info, Iam-hiQ and r²based indices can be derived from standard output-files of imputation software. Sample/probe and marker filtering is possible. This allows e.g. accurate marker filtering ahead of data analysis. A Python code is available but also a stand-alone executable file. Availability and Implementation: The source code (Python version 3.9.4), a stand-alone executive file, and example data for ImputAccur are freely available at https://gitlab.gwdg.de/kolja.thormann1/imputationquality.git . Supplementary Information: Supplementary information is available at Bioinformatics online. Contact: arosenb@gwdg.de or koljaalexander.thormann@uni-goettingen.de
- Open Access
- 10 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
A Tutorial on Multiple Extended Object Tracking
This tutorial introduces state-of-the-art methods for tracking multiple spatially extended objects based on unlabeled noisy point clouds, e.g., from radar or lidar sensors. In the first part, the focus lies on tracking a single extended object, i.e., the objective is to simultaneously estimate the shape and position of a moving object based on spatially distributed noisy detections. Model-based approaches for tracking elliptical and star-convex shaped objects are treated. Furthermore, recent learning-based approaches are discussed, which learn the spatial distribution of detections from real data. The second part considers the track management and data association problem, i.e., the initialization and termination of tracks as well as the association of detections to objects. After an in-depth analysis of the data association problem for extended objects, various data association approaches are discussed. Finally, recent frameworks for multiple extended object tracking are introduced such as the random finite set-based Poisson multi-Bernoulli mixture framework.
- 10 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessA Tutorial on Multiple Extended Object Tracking
This tutorial introduces state-of-the-art methods for tracking multiple spatially extended objects based on unlabeled noisy point clouds, e.g., from radar or lidar sensors. In the first part, the focus lies on tracking a single extended object, i.e., the objective is to simultaneously estimate the shape and position of a moving object based on spatially distributed noisy detections. Model-based approaches for tracking elliptical and star-convex shaped objects are treated. Furthermore, recent learning-based approaches are discussed, which learn the spatial distribution of detections from real data. The second part considers the track management and data association problem, i.e., the initialization and termination of tracks as well as the association of detections to objects. After an in-depth analysis of the data association problem for extended objects, various data association approaches are discussed. Finally, recent frameworks for multiple extended object tracking are introduced such as the random finite set-based Poisson multi-Bernoulli mixture framework.
- Open Access
Continuous Herded Gibbs Sampling
Herding is a technique to sequentially generate deterministic samples from a probability distribution. In this work, we propose a continuous herded Gibbs sampler that combines kernel herding on continuous densities with the Gibbs sampling idea. Our algorithm allows for deterministically sampling from high-dimensional multivariate probability densities, without directly sampling from the joint density. Experiments with Gaussian mixture densities indicate that the L2 error decreases similarly to kernel herding, while the computation time is significantly lower, i.e., linear in the number of dimensions.
Open AccessContinuous Herded Gibbs Sampling
Herding is a technique to sequentially generate deterministic samples from a probability distribution. In this work, we propose a continuous herded Gibbs sampler that combines kernel herding on continuous densities with the Gibbs sampling idea. Our algorithm allows for deterministically sampling from high-dimensional multivariate probability densities, without directly sampling from the joint density. Experiments with Gaussian mixture densities indicate that the L2 error decreases similarly to kernel herding, while the computation time is significantly lower, i.e., linear in the number of dimensions.