Michael Breuß
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
Research Subjects
Michael Breuß has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Marvin Kahra
Brandenburg Technical University Cottbus-Senftenberg
11 shared publications - Andreas Kleefeld
Forschungszentrum Jülich GmbH, Jülich Supercomputing Centre, Jülich, Germany
10 shared publications - Ashkan Mansouri Yarahmadi
BTU Cottbus-Senftenberg
9 shared publications - Laurent Hoeltgen
Saarland University
7 shared publications - Martin Welk
UMIT TIROL -Private University for Health Sciences and Health Technology Eduard-Wallnöfer-Zentrum 1 6060 Hall/ Tyrol Austria
7 shared publications - Shima Shabani
Brandenburg University of Technology
7 shared publications
Latest Publications
- 14 August 2026
- Published by Springer Nature
- p. 70-90
PCA-Based Interpretable Knowledge Representation and Analysis of Geometric Design Parameters
- 14 August 2026
- Published by Springer Nature
- p. 70-90
PCA-Based Interpretable Knowledge Representation and Analysis of Geometric Design Parameters
- Open Access
- 1 August 2026
- Published by Springer Nature in Optimization and Engineering
- p. 1-42
Autonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Location-Allocation Optimization and Flight Trajectory Planning
Drowning is among the most prevalent causes of death from unintentional injuries worldwide. Because of the time-sensitive nature of swimming accidents and the shortage of lifeguard staff resulting in unsupervised swimming areas, interest in innovative supportive rescue methods increases. In this paper, we introduce an autonomous Unmanned Aircraft System (UAS) that can be employed by Emergency Medical Service (EMS) providers in swimmer rescue scenarios additionally to Standard Rescue Operation (SRO) equipment. The UAS consists of Unmanned Aerial Vehicles (UAVs) and purpose-built hangars located near the swimming area to store the UAVs. When receiving an alert, the UAVs autonomously navigate to the emergency site to conduct a Search and Rescue (S&R) operation for the swimmer in distress. We introduce a Mixed-Integer Linear Programming (MILP) model to address the Facility Location-Allocation Problem (FALP), identifying optimal hangar locations and allocation of UAVs to hangars to serve the demand in the swimming area. Additionally, we present a MILP model to optimize the UAV flight trajectories in advance of the operation, allowing for efficient coordination of a heterogeneous UAV swarm. We apply the presented MILP models to a real-world scenario in the Lusatian Lake District, Eastern Germany using the state-of-the-art commercial solver CPLEX to solve the instances.
- 1 August 2026
- Published by Springer Nature in Optimization and Engineering
- p. 1-42
Open AccessAutonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Location-Allocation Optimization and Flight Trajectory Planning
Drowning is among the most prevalent causes of death from unintentional injuries worldwide. Because of the time-sensitive nature of swimming accidents and the shortage of lifeguard staff resulting in unsupervised swimming areas, interest in innovative supportive rescue methods increases. In this paper, we introduce an autonomous Unmanned Aircraft System (UAS) that can be employed by Emergency Medical Service (EMS) providers in swimmer rescue scenarios additionally to Standard Rescue Operation (SRO) equipment. The UAS consists of Unmanned Aerial Vehicles (UAVs) and purpose-built hangars located near the swimming area to store the UAVs. When receiving an alert, the UAVs autonomously navigate to the emergency site to conduct a Search and Rescue (S&R) operation for the swimmer in distress. We introduce a Mixed-Integer Linear Programming (MILP) model to address the Facility Location-Allocation Problem (FALP), identifying optimal hangar locations and allocation of UAVs to hangars to serve the demand in the swimming area. Additionally, we present a MILP model to optimize the UAV flight trajectories in advance of the operation, allowing for efficient coordination of a heterogeneous UAV swarm. We apply the presented MILP models to a real-world scenario in the Lusatian Lake District, Eastern Germany using the state-of-the-art commercial solver CPLEX to solve the instances.
- Open Access
Deep Learning for Unsupervised 3D Shape Representation with Superquadrics
The representation of 3D shapes from point clouds remains a fundamental challenge in computer vision. A common approach decomposes 3D objects into interpretable geometric primitives, enabling compact, structured, and efficient representations. Building upon prior frameworks, this study introduces an enhanced unsupervised deep learning approach for 3D shape representation using superquadrics. The proposed framework fits a set of superquadric primitives to 3D objects through a fully integrated, differentiable pipeline that enables efficient optimization and parameter learning, directly extracting geometric structure from 3D point clouds without requiring ground-truth segmentation labels. This work introduces three key advancements that substantially improve representation quality, interpretability, and evaluation rigor: (1) A uniform sampling strategy that enhances training stability compared with random sampling used in earlier models; (2) An overlapping loss that penalizes intersections between primitives, reducing redundancy and improving reconstruction coherence; and (3) A novel evaluation framework comprising Primitive Accuracy, Structural Accuracy, and Overlapping Percentage metrics. This new metric design transitions from point-based to structure-aware assessment, enabling fairer and more interpretable comparison across primitive-based models. Comprehensive evaluations on benchmark 3D shape datasets demonstrate that the proposed modifications yield coherent, compact, and semantically consistent shape representations, establishing a robust foundation for interpretable and quantitative evaluation in primitive-based 3D reconstruction.
Open AccessDeep Learning for Unsupervised 3D Shape Representation with Superquadrics
The representation of 3D shapes from point clouds remains a fundamental challenge in computer vision. A common approach decomposes 3D objects into interpretable geometric primitives, enabling compact, structured, and efficient representations. Building upon prior frameworks, this study introduces an enhanced unsupervised deep learning approach for 3D shape representation using superquadrics. The proposed framework fits a set of superquadric primitives to 3D objects through a fully integrated, differentiable pipeline that enables efficient optimization and parameter learning, directly extracting geometric structure from 3D point clouds without requiring ground-truth segmentation labels. This work introduces three key advancements that substantially improve representation quality, interpretability, and evaluation rigor: (1) A uniform sampling strategy that enhances training stability compared with random sampling used in earlier models; (2) An overlapping loss that penalizes intersections between primitives, reducing redundancy and improving reconstruction coherence; and (3) A novel evaluation framework comprising Primitive Accuracy, Structural Accuracy, and Overlapping Percentage metrics. This new metric design transitions from point-based to structure-aware assessment, enabling fairer and more interpretable comparison across primitive-based models. Comprehensive evaluations on benchmark 3D shape datasets demonstrate that the proposed modifications yield coherent, compact, and semantically consistent shape representations, establishing a robust foundation for interpretable and quantitative evaluation in primitive-based 3D reconstruction.
- 1 November 2025
- Published by Springer Nature
- p. 429-442
Morphological Leveling Based on the Log-Exp-Supremum for Colour Images
- 1 November 2025
- Published by Springer Nature
- p. 429-442
Morphological Leveling Based on the Log-Exp-Supremum for Colour Images
- 1 November 2025
- Published by Springer Nature
- p. 401-414
Morphological PDEs with Rotationally Invariant Space-Fractional Derivatives
- 1 November 2025
- Published by Springer Nature
- p. 401-414
Morphological PDEs with Rotationally Invariant Space-Fractional Derivatives
- 1 November 2025
- Published by Springer Nature
- p. 487-500
Morphological Granulometric Analysis of Particle Imagery from Microgravity Experiments
- 1 November 2025
- Published by Springer Nature
- p. 487-500
Morphological Granulometric Analysis of Particle Imagery from Microgravity Experiments
- Open Access
- 23 October 2025
- Published by MDPI AG in Preprints.org
Deep Learning for Unsupervised 3D Shape Representation with Superquadrics
The representation of three-dimensional (3D) shapes from point clouds remains a fundamental challenge in computer vision. A common approach decomposes 3D objects into interpretable geometric primitives, enabling compact, structured, and efficient representations. Building upon prior frameworks, this study introduces an enhanced unsupervised deep learning approach for 3D shape representation using superquadrics. The proposed framework fits a set of superquadric primitives to 3D objects through a fully integrated, differentiable pipeline that enables efficient optimization and parameter learning, directly extracting geometric structure from 3D point clouds without requiring ground-truth segmentation labels. This work introduces three key advancements that substantially improve representation quality, interpretability, and evaluation rigor: (1) a uniform sampling strategy that enhances training stability compared with random sampling used in earlier models; (2) an overlapping loss that penalizes intersections between primitives, reducing redundancy and improving reconstruction coherence; and (3) a novel evaluation framework comprising \emph{Primitive Accuracy}, \emph{Structural Accuracy}, and \emph{Overlapping Percentage} metrics. This new metric design transitions from point-based to structure-aware assessment, enabling fairer and more interpretable comparison across primitive-based models. Comprehensive evaluations on benchmark 3D shape datasets demonstrate that the proposed modifications yield coherent, compact, and semantically consistent shape representations, establishing a robust foundation for interpretable and quantitative evaluation in primitive-based 3D reconstruction.
- 23 October 2025
- Published by MDPI AG in Preprints.org
Open AccessDeep Learning for Unsupervised 3D Shape Representation with Superquadrics
The representation of three-dimensional (3D) shapes from point clouds remains a fundamental challenge in computer vision. A common approach decomposes 3D objects into interpretable geometric primitives, enabling compact, structured, and efficient representations. Building upon prior frameworks, this study introduces an enhanced unsupervised deep learning approach for 3D shape representation using superquadrics. The proposed framework fits a set of superquadric primitives to 3D objects through a fully integrated, differentiable pipeline that enables efficient optimization and parameter learning, directly extracting geometric structure from 3D point clouds without requiring ground-truth segmentation labels. This work introduces three key advancements that substantially improve representation quality, interpretability, and evaluation rigor: (1) a uniform sampling strategy that enhances training stability compared with random sampling used in earlier models; (2) an overlapping loss that penalizes intersections between primitives, reducing redundancy and improving reconstruction coherence; and (3) a novel evaluation framework comprising \emph{Primitive Accuracy}, \emph{Structural Accuracy}, and \emph{Overlapping Percentage} metrics. This new metric design transitions from point-based to structure-aware assessment, enabling fairer and more interpretable comparison across primitive-based models. Comprehensive evaluations on benchmark 3D shape datasets demonstrate that the proposed modifications yield coherent, compact, and semantically consistent shape representations, establishing a robust foundation for interpretable and quantitative evaluation in primitive-based 3D reconstruction.
- Open Access
- 19 September 2025
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 67 (5) , 1-28
Matrix-Valued LogSumExp Approximation for Colour Morphology
Mathematical morphology is a part of image processing that employs a moving window to modify pixel values through the application of specific operations. The supremum and infimum are pivotal concepts, yet defining them in a general sense for high-dimensional data such as colour is a challenging endeavour. As a result, a number of different approaches have been taken to try to find a solution, with certain compromises being made along the way. In this paper, we present an analysis of a novel approach that replaces the supremum within a morphological operation with the LogExp approximation of the maximum for matrix-valued colours. This approach has the advantage of extending the associativity of dilation from the one-dimensional to the higher-dimensional case. Furthermore, the minimality property is investigated and a relaxation specified to ensure that the approach is continuously dependent on the input data.
- 19 September 2025
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 67 (5) , 1-28
Open AccessMatrix-Valued LogSumExp Approximation for Colour Morphology
Mathematical morphology is a part of image processing that employs a moving window to modify pixel values through the application of specific operations. The supremum and infimum are pivotal concepts, yet defining them in a general sense for high-dimensional data such as colour is a challenging endeavour. As a result, a number of different approaches have been taken to try to find a solution, with certain compromises being made along the way. In this paper, we present an analysis of a novel approach that replaces the supremum within a morphological operation with the LogExp approximation of the maximum for matrix-valued colours. This approach has the advantage of extending the associativity of dilation from the one-dimensional to the higher-dimensional case. Furthermore, the minimality property is investigated and a relaxation specified to ensure that the approach is continuously dependent on the input data.
- 22 August 2025
- Published by Springer Nature
- p. 309-327
Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage
- 22 August 2025
- Published by Springer Nature
- p. 309-327
Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage
- 22 August 2025
- Published by Springer Nature
- p. 288-308
Object Detection Characteristics in a Learning Factory Environment using YOLOv8
- 22 August 2025
- Published by Springer Nature
- p. 288-308
Object Detection Characteristics in a Learning Factory Environment using YOLOv8