Michael Breuß
YOU?
Author Swipe
View article: Deep Learning for Unsupervised 3D Shape Representation with Superquadrics
Deep Learning for Unsupervised 3D Shape Representation with Superquadrics Open
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 ef…
View article: Matrix-Valued LogSumExp Approximation for Colour Morphology
Matrix-Valued LogSumExp Approximation for Colour Morphology Open
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 f…
View article: Fuzzy Frankot–Chellappa Algorithm for Surface Normal Integration
Fuzzy Frankot–Chellappa Algorithm for Surface Normal Integration Open
In this paper, we propose a fuzzy formulation of the classic Frankot–Chellappa algorithm by which surfaces can be reconstructed using normal vectors. In the fuzzy formulation, the surface normal vectors may be uncertain or ambiguous, yield…
View article: Recognition of Geometrical Shapes by Dictionary Learning
Recognition of Geometrical Shapes by Dictionary Learning Open
Dictionary learning is a versatile method to produce an overcomplete set of vectors, called atoms, to represent a given input with only a few atoms. In the literature, it has been used primarily for tasks that explore its powerful represen…
View article: Object detection characteristics in a learning factory environment using YOLOv8
Object detection characteristics in a learning factory environment using YOLOv8 Open
AI-based object detection, and efforts to explain and investigate their characteristics, is a topic of high interest. The impact of, e.g., complex background structures with similar appearances as the objects of interest, on the detection …
View article: Matrix-Valued LogSumExp Approximation for Colour Morphology
Matrix-Valued LogSumExp Approximation for Colour Morphology Open
Mathematical morphology is a part of image processing that uses a window that moves across the image to change certain pixels according to certain operations. The concepts of supremum and infimum play a crucial role here, but it proves cha…
View article: An Improved Frankot and Chellappa Method for Surface Normal Integration Using Fuzzy Concepts
An Improved Frankot and Chellappa Method for Surface Normal Integration Using Fuzzy Concepts Open
In this paper, we propose the Fuzzy formulation of the classic Frankot-Chellappa method by which surfaces can be reconstructed using normal vectors. In the Fuzzy formulation, the surface normal vectors may be uncertain or ambiguous. The un…
View article: Dictionary Learning with the K-SVDAlgorithm for Recovery of Highly Textured Images
Dictionary Learning with the K-SVDAlgorithm for Recovery of Highly Textured Images Open
Image recovery by dictionary learning is of potential interest for many possible applications. To learn a dictionary, one needs to solve a minimization problem where the solution should be sparse. The K-SVD formalism, which is a generaliza…
View article: A First Approach to Quantum Logical Shape Classification Framework
A First Approach to Quantum Logical Shape Classification Framework Open
Quantum logic is a well-structured theory, which has recently received some attention because of its fundamental relation to quantum computing. However, the complex foundation of quantum logic borrowing concepts from different branches of …
View article: Investigating Training Datasets of Real and Synthetic Images for Outdoor Swimmer Localisation with YOLO
Investigating Training Datasets of Real and Synthetic Images for Outdoor Swimmer Localisation with YOLO Open
In this study, we developed and explored a methodical image augmentation technique for swimmer localisation in northern German outdoor lake environments. When it comes to enhancing swimmer safety, a main issue we have to deal with is the l…
View article: A First Approach to Quantum Logical Shape Classification Framework
A First Approach to Quantum Logical Shape Classification Framework Open
Quantum logic is a well-structured theory, which has recently received some attention because of its fundamental relation to quantum computing. However, the complex foundation of quantum logic borrowing concepts from different branches of …
View article: Investigating training datasets of real and synthetic images for swimmer localisation with YOLO
Investigating training datasets of real and synthetic images for swimmer localisation with YOLO Open
In this paper we develop and explore a methodical pipeline for swimmer localisation in outdoor environments. The developed framework is intended to be used for enhancing swimmer safety. A main issue we deal with by the proposed approach is…
View article: An Approach to Colour Morphological Supremum Formation using the LogSumExp Approximation
An Approach to Colour Morphological Supremum Formation using the LogSumExp Approximation Open
Mathematical morphology is a part of image processing that has proven to be fruitful for numerous applications. Two main operations in mathematical morphology are dilation and erosion. These are based on the construction of a supremum or i…
View article: Adaptive neural-domain refinement for solving time-dependent differential equations
Adaptive neural-domain refinement for solving time-dependent differential equations Open
A classic approach for solving differential equations with neural networks builds upon neural forms, which employ the differential equation with a discretisation of the solution domain. Making use of neural forms for time-dependent differe…
View article: Morphological Sampling Theorem and its Extension to Grey-value Images
Morphological Sampling Theorem and its Extension to Grey-value Images Open
Sampling is a basic operation in image processing. In classic literature, a morphological sampling theorem has been established, which shows how sampling interacts by morphological operations with image reconstruction. Many aspects of morp…
View article: The Polynomial Connection between Morphological Dilation and Discrete Convolution
The Polynomial Connection between Morphological Dilation and Discrete Convolution Open
In this paper we consider the fundamental operations dilation and erosion of mathematical morphology. Many powerful image filtering operations are based on their combinations. We establish homomorphism between max-plus semi-ring of integer…
View article: On the Regularising Levenberg-Marquardt Method for Blinn-Phong Photometric Stereo
On the Regularising Levenberg-Marquardt Method for Blinn-Phong Photometric Stereo Open
Photometric stereo refers to the process to compute the 3D shape of an object using information on illumination and reflectance from several input images from the same point of view. The most often used reflectance model is the Lambertian …
View article: Long Short-Term Memory Neural Network for Temperature Prediction in Laser Powder Bed Additive Manufacturing
Long Short-Term Memory Neural Network for Temperature Prediction in Laser Powder Bed Additive Manufacturing Open
In context of laser powder bed fusion (L-PBF), it is known that the properties of the final fabricated product highly depend on the temperature distribution and its gradient over the manufacturing plate. In this paper, we propose a novel m…
View article: YOLO-based Object Detection in Industry 4.0 Fischertechnik Model Environment
YOLO-based Object Detection in Industry 4.0 Fischertechnik Model Environment Open
In this paper we extensively explore the suitability of YOLO architectures to monitor the process flow across a Fischertechnik industry 4.0 application. Specifically, different YOLO architectures in terms of size and complexity design alon…
View article: Properties of Morphological Dilation in Max-Plus and Plus-Prod Algebra in Connection with the Fourier Transformation
Properties of Morphological Dilation in Max-Plus and Plus-Prod Algebra in Connection with the Fourier Transformation Open
The basic filters in mathematical morphology are dilation and erosion. They are defined by a structuring element that is usually shifted pixel-wise over an image, together with a comparison process that takes place within the corresponding…
View article: Photometric Stereo with Non-Lambertian Preprocessing and Hayakawa Lighting Estimation for Highly Detailed Shape Reconstruction
Photometric Stereo with Non-Lambertian Preprocessing and Hayakawa Lighting Estimation for Highly Detailed Shape Reconstruction Open
View article: Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information
Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information Open
This paper presents a novel approach to distinguishing driving styles with respect to their energy efficiency. A distinct property of our method is that it relies exclusively on the global positioning system (GPS) logs of drivers. This set…
View article: Computational Analysis of PDE-Based Shape Analysis Models by Exploring the Damped Wave Equation
Computational Analysis of PDE-Based Shape Analysis Models by Exploring the Damped Wave Equation Open
The computation of correspondences between shapes is a principal task in shape analysis. In this work, we consider correspondences constructed by a numerical solution of partial differential equations (PDEs). The underlying model of intere…
View article: Efficient Long-Term Simulation of the Heat Equation with Application in Geothermal Energy Storage
Efficient Long-Term Simulation of the Heat Equation with Application in Geothermal Energy Storage Open
Long-term evolutions of parabolic partial differential equations, such as the heat equation, are the subject of interest in many applications. There are several numerical solvers marking the state-of-the-art in diverse scientific fields th…
View article: Computational characteristics of feedforward neural networks for solving a stiff differential equation
Computational characteristics of feedforward neural networks for solving a stiff differential equation Open
Feedforward neural networks offer a possible approach for solving differential equations. However, the reliability and accuracy of the approximation still represent delicate issues that are not fully resolved in the current literature. Com…
View article: Fast Shape Classification Using Kolmogorov-Smirnov Statistics
Fast Shape Classification Using Kolmogorov-Smirnov Statistics Open
The fast classification of shapes is an important problem in shape analysis and of high relevance for many possible applications. In this paper, we consider the use of very fast and easy to compute statistical techniques for assessing shap…
View article: Collocation polynomial neural forms and domain fragmentation for solving initial value problems
Collocation polynomial neural forms and domain fragmentation for solving initial value problems Open
Several neural network approaches for solving differential equations employ trial solutions with a feedforward neural network. There are different means to incorporate the trial solution in the construction, for instance, one may include t…
View article: Adaptive neural domain refinement for solving time-dependent differential equations
Adaptive neural domain refinement for solving time-dependent differential equations Open
A classic approach for solving differential equations with neural networks builds upon neural forms, which employ the differential equation with a discretisation of the solution domain. Making use of neural forms for time-dependent differe…
View article: Collocation Polynomial Neural Forms and Domain Fragmentation for solving Initial Value Problems
Collocation Polynomial Neural Forms and Domain Fragmentation for solving Initial Value Problems Open
Several neural network approaches for solving differential equations employ trial solutions with a feedforward neural network. There are different means to incorporate the trial solution in the construction, for instance one may include th…
View article: Collocation Polynomial Neural Forms and Domain Fragmentation for Initial Value Problems.
Collocation Polynomial Neural Forms and Domain Fragmentation for Initial Value Problems. Open
Several neural network approaches for solving differential equations employ trial solutions with a feedforward neural network. There are different means to incorporate the trial solution in the construction, for instance one may include th…