Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

Reset filters

Settings
Now showing 1 - 10 of 2668
  • Publication
    Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems
    ( 2023)
    Rueden, Laura von
    ;
    Mayer, Sebastian
    ;
    Beckh, Katharina
    ;
    Georgiev, Bogdan
    ;
    Giesselbach, Sven
    ;
    Heese, Raoul
    ;
    Kirsch, Birgit
    ;
    Walczak, Michal
    ;
    Pfrommer, Julius
    ;
    Pick, Annika
    ;
    Ramamurthy, Rajkumar
    ;
    Garcke, Jochen
    ;
    Bauckhage, Christian
    ;
    Schuecker, Jannis
    Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
  • Publication
    Data-Driven Fault Detection in Industrial Batch Processes Based on a Stochastic Hybrid Process Model
    ( 2022)
    Windmann, Stefan
    This paper presents a novel fault detection approach for industrial batch processes. The batch processes under consideration are characterized by the interaction between discrete system modes and non-stationary continuous dynamics. Therefore, a stochastic hybrid process model (SHPM) is introduced, where process variables are modeled as time-variant Gaussian distributions, which depend on hidden system modes. Transitions between the system modes are assumed to be either autonomous or to be triggered by observable events such as on/off signals. The model parameters are determined from training data using expectation-maximization techniques. A new fault detection algorithm is proposed, which assesses the likelihoods of sensor signals on the basis of the stochastic hybrid process model. Evaluation of the proposed fault detection system has been conducted for a penicillin production process, with the results showing a significant improvement over the existing baseline methods.
  • Publication
    Where are we with Human Pose Estimation in Real-World Surveillance?
    ( 2022)
    Cormier, Mickael
    ;
    Clepe, Aris
    ;
    Specker, Andreas
    ;
    Beyerer, Jürgen
    The rapidly increasing number of surveillance cameras offers a variety of opportunities for intelligent video analytics to improve public safety. Among many others, the automatic recognition of suspicious and violent behavior poses a key task. To preserve personal privacy, prevent ethnic bias, and reduce complexity, most approaches first extract the pose or skeleton of persons and subsequently perform activity recognition. However, current literature mainly focuses on research datasets and does not consider real-world challenges and requirements of human pose estimation. We close this gap by analyzing these challenges, such as inadequate data and the need for real-time processing, and proposing a framework for human pose estimation in uncontrolled crowded surveillance scenarios. Our system integrates mitigation measures as well as a tracking component to incorporate temporal information. Finally, we provide a detailed quantitative and qualitative analysis on both a scientific and a real-world dataset to highlight improvements and remaining obstacles towards robust real-world human pose estimation in uncooperative scenarios.
  • Publication
    MotorFactory: A Blender Add-on for Large Dataset Generation of Small Electric Motors
    ( 2022)
    Wu, Chengzhi
    ;
    Zhou, Kanran
    ;
    Kaiser, Jan-Philipp
    ;
    Mitschke, Norbert
    ;
    Klein, Jan-Felix
    ;
    Pfrommer, Julius
    ;
    Beyerer, Jürgen
    ;
    Lanza, Gisela
    ;
    Heizmann, Michael
    ;
    Furmans, Kai
    To enable automatic disassembly of different product types with uncertain condition and degree of wear in remanufacturing, agile production systems that can adapt dynamically to changing requirements are needed. Machine learning algorithms can be employed due to their generalization capabilities of learning from various types and variants of products. However, in reality, datasets with a diversity of samples that can be used to train models are difficult to obtain in the initial period. This may cause bad performances when the system tries to adapt to new unseen input data in the future. In order to generate large datasets for different learning purposes, in our project, we present a Blender add-on named MotorFactory to generate customized mesh models of various motor instances. MotorFactory allows to create mesh models which, complemented with additional add-ons, can be further used to create synthetic RGB images, depth images, normal images, segmentation ground truth masks and 3D point cloud datasets with point-wise semantic labels. The created synthetic datasets may be used for various tasks including motor type classification, object detection for decentralized material transfer tasks, part segmentation for disassembly and handling tasks, or even reinforcement learning-based robotics control or view-planning.
  • Publication
    Composition and Symmetries - Computational Analysis of Fine-Art Aesthetics
    ( 2022)
    Zhuravleva, Olga A.
    ;
    Komarov, Andrei V.
    ;
    Zherdev, Denis A.
    ;
    Savkhalova, Natalie B.
    ;
    Demina, Anna L.
    ;
    Michaelsen, Eckart
    ;
    Nikonorov, Artem V.
    ;
    Nesterov, Alexander Y.
    This article deals with the problem of quantitative research of the aesthetic content of the fine-art object. The paper states that a fine-art object is a conceptually formed sequence of signs, and its composition is a structural form, that can be measured using mathematical models. The main approach is based on the perception of the formal order as a determinant of the aesthetic category of beauty. The composition of the image is directly related to the formation of aesthetic sensations and values, since it performs the function of controlling the viewer's perception of a work of art. The research is based on the studies of computational aesthetics by G. D. Birkhoff and M. Bense, as well as the studies of the receptive aesthetics of R. Ingarden, W. Iser, H. R. Jauss and Ya. Mukarzhovsky. The computational aesthetics methods, such as CNN-based object detectors, and gestalt-based symmetry analysis, are used to detect symmetry axes in fine-art images. Experimental analysis demonstrates that the applied computational approach is consistent with the philosophical analysis and the expert evaluations of the fine-art images, therefore it allows to obtain more detailed fine-art paintings description.
  • Publication
    Towards a Better Understanding of Machine Learning based Network Intrusion Detection Systems in Industrial Networks
    ( 2022)
    Borcherding, Anne
    ;
    Feldmann, Lukas
    ;
    Karch, Markus
    ;
    Meshram, Ankush
    ;
    Beyerer, Jürgen
    It is crucial in an industrial network to understand how and why a intrusion detection system detects, classifies, and reports intrusions. With the ongoing introduction of machine learning into the research area of intrusion detection, this understanding gets even more important since the used systems often appear as a black-box for the user and are no longer understandable in an intuitive and comprehensible way. We propose a novel approach to understand the internal characteristics of a machine learning based network intrusion detection system. This approach includes methods to understand which data sources the system uses, to evaluate whether the system uses linear or non-linear classification approaches, and to find out which underlying machine learning model is implemented in the system. Our evaluation on two publicly available industrial datasets shows that the detection of the data source and the differentiation between linear and non-linear models is possible with our approach. In addition, the identification of the underlying machine learning model can be accomplished with statistical significance for non-linear models. The information made accessible by our approach helps to develop a deeper understanding of the functioning of a network intrusion detection system, and contributes towards developing transparent machine learning based intrusion detection approaches.
  • Publication
    Improving Semantic Image Segmentation via Label Fusion in Semantically Textured Meshes
    ( 2022)
    Fervers, Florian
    ;
    Breuer, Timo
    ;
    Stachowiak, Gregor
    ;
    Bullinger, Sebastian
    ;
    Bodensteiner, Christoph
    ;
    Arens, Michael
    Models for semantic segmentation require a large amount of hand-labeled training data which is costly and time-consuming to produce. For this purpose, we present a label fusion framework that is capable of improving semantic pixel labels of video sequences in an unsupervised manner. We make use of a 3D mesh representation of the environment and fuse the predictions of different frames into a consistent representation using semantic mesh textures. Rendering the semantic mesh using the original intrinsic and extrinsic camera parameters yields a set of improved semantic segmentation images. Due to our optimized CUDA implementation, we are able to exploit the entire c-dimensional probability distribution of annotations over c classes in an uncertainty-aware manner. We evaluate our method on the Scannet dataset where we improve annotations produced by the state-of-the-art segmentation network ESANet from 52.05% to 58.25% pixel accuracy. We publish the source code of our framework online to foster future research in this area (https://github.com/fferflo/semantic-meshes). To the best of our knowledge, this is the first publicly available label fusion framework for semantic image segmentation based on meshes with semantic textures.
  • Publication
    Fast and Lightweight Online Person Search for Large-Scale Surveillance Systems
    ( 2022)
    Specker, Andreas
    ;
    Moritz, Lennart
    ;
    Cormier, Mickael
    ;
    Beyerer, Jürgen
    The demand for methods for video analysis in the fieldof surveillance technology is rapidly growing due to theincreasing amount of surveillance footage available. Intelligent methods for surveillance software offer numerouspossibilities to support police investigations and crime prevention. This includes the integration of video processingpipelines for tasks such as detection of graffiti, suspiciousluggage, or intruders. Another important surveillance taskis the semi-automated search for specific persons-of-interestwithin a camera network. In this work, we identify the major obstacles for the development of person search systemsas the real-time processing capability on affordable hardware and the performance gap of person detection and reidentification methods on unseen target domain data. Inaddition, we demonstrate the current potential of intelligentonline person search by developing a real-world, largescale surveillance system. An extensive evaluation is provided for person detection, tracking, and re-identificationcomponents on affordable hardware setups, for which thewhole system achieves real-time processing up to 76 FPS.
  • Publication
    Model-assisted DoE applied to microalgae processes
    ( 2022)
    Gassenmeier, Veronika
    ;
    Deppe, Sahar
    ;
    Hernández Rodríguez, Tanja
    ;
    Kuhfuß, Fabian
    ;
    Moser, Andre
    ;
    Hass, Volker C.
    ;
    Kuchemüller, Kim B.
    ;
    Pörtner, Ralf
    ;
    Möller, Johannes
    ;
    Ifrim, George
    ;
    Frahm, Björn
    This study assesses the performance of the model-assisted Design of Experiment (mDoE) software toolbox for the design of two microalgae bioprocesses. The mDoE-toolbox was applied to maximize biomass growth for Desmodesmus pseudocommunis in a photobioreactor by varying the light intensity and pH and for Chlorella vulgaris in shake flasks, by varying the light intensity and duration. For both case studies, a mathematical mechanistic model was applied. In the first study only one experiment was necessary to adapt the mathematical model and identify a combination of light intensity and pH that improved biomass yield, as confirmed experimentally. In the second study, no well-established model was available for the specific experimental arrangement. On the basis of the literature, a mathematical model was constructed and a first cycle of mDoE was performed, thus identifying the desired factor combinations. Experiments confirmed the high biomass yield but revealed shortcomings of the model. The model was improved and a second cycle of mDoE was performed. The recommended factor combinations from both cycles were comparable. The mDoE was found to be a time-saving, cost-effective and useful method enabling the identification of factor combinations leading to high biomass production for the design of two different microalgae bioprocesses with low experimental effort.
  • Publication
    Handheld spectral sensing devices should not mislead consumers as far as non-authentic food is concerned: A case study with adulteration of milk powder
    ( 2022)
    Delatour, Thierry
    ;
    Becker, Florian
    ;
    Krause, Julius
    ;
    Romero, Roman
    ;
    Gruna, Robin
    ;
    Längle, Thomas
    ;
    Panchaud, Alexandre
    With the rising trend of consumers being offered by start-up companies portable devices and applications for checking quality of purchased products, it appears of paramount importance to assess the reliability of miniaturized sensors embedded in such devices. Here, eight sensors were assessed for food fraud applications in skimmed milk powder. The performance was evaluated with dry- and wet-blended powders mimicking adulterated materials by addition of either ammonium sulfate, semicarbazide, or cornstarch in the range 0.5-10% of profit. The quality of the spectra was assessed for an adequate identification of the outliers prior to a deep assessment of performance for both non-targeted (soft independent modelling of class analogy, SIMCA) and targeted analyses (partial least square regression with orthogonal signal correction, OPLS). Here, we show that the sensors have generally difficulties in detecting adulterants at ca. 5% supplementation, and often fail in achieving adequate specificity and detection capability. This is a concern as they may mislead future users, particularly consumers, if they are intended to be developed for handheld devices available publicly in smartphone-based applications. Full article(This article belongs to the Special Issue Rapid Detection Methods for Food Fraud and Food Contaminants Series II).