Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters
Reset filters

Settings
Now showing 1 - 10 of 105
  • 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
    Sovereign Digital Consent through Privacy Impact Quantification and Dynamic Consent
    ( 2022)
    Appenzeller, Arno
    ;
    Hornung, Marina
    ;
    Kadow, Thomas
    ;
    Krempel, Erik
    ;
    Beyerer, Jürgen
    Digitization is becoming more and more important in the medical sector. Through electronic health records and the growing amount of digital data of patients available, big data research finds an increasing amount of use cases. The rising amount of data and the imposing privacy risks can be overwhelming for patients, so they can have the feeling of being out of control of their data. Several previous studies on digital consent have tried to solve this problem and empower the patient. However, there are no complete solution for the arising questions yet. This paper presents the concept of Sovereign Digital Consent by the combination of a consent privacy impact quantification and a technology for proactive sovereign consent. The privacy impact quantification supports the patient to comprehend the potential risk when sharing the data and considers the personal preferences regarding acceptance for a research project. The proactive dynamic consent implementation provides an implementation for fine granular digital consent, using medical data categorization terminology. This gives patients the ability to control their consent decisions dynamically and is research friendly through the automatic enforcement of the patients' consent decision. Both technologies are evaluated and implemented in a prototypical application. With the combination of those technologies, a promising step towards patient empowerment through Sovereign Digital Consent can be made.
  • Publication
  • Publication
    A Step Towards Global Counterfactual Explanations: Approximating the Feature Space Through Hierarchical Division and Graph Search
    ( 2021)
    Becker, Maximilian
    ;
    Burkart, Nadia
    ;
    Birnstill, Pascal
    ;
    Beyerer, Jürgen
    The field of Explainable Artificial Intelligence (XAI) tries to make learned models more understandable. One type of explanation for such models are counterfactual explanations. Counterfactual explanations explain the decision for a specific instance, the factual, by providing a similar instance which leads to a different decision, the counterfactual. In this work a new approaches around the idea of counterfactuals was developed. It generates a data structure over the feature space of a classification problem to accelerate the search for counterfactuals and augments them with global explanations. The approach maps the feature space by hierarchically dividing it into regions which belong to the same class. It is applicable in any case where predictions can be generated for input data, even without direct access to the model. The framework works well for lower-dimensional problems but becomes unpractical due to high computation times at around 12 to 15 dimensions.
  • Publication
    Direct-imaging DOEs for high-NA multi-spot confocal surface measurement
    ( 2021)
    Li, Zheng
    ;
    Taphanel, Miro
    ;
    Längle, Thomas
    ;
    Beyerer, Jürgen
    Diffractive lens arrays with overlapping apertures can produce spot arrays with high numerical apertures (NAs). Combined with low-NA objectives, they can measure a large area with high lateral resolution. However, for surface measurements, the axial resolution of such setups is still fundamentally limited by the objectives. In this work, we propose a new design of diffractive optical elements (DOEs) to overcome this problem. The proposed Direct-imaging DOEs can perform 3D high-NA multi-spot surface measurements. Laterally, a non-vanishing contrast up to 1448 lp/mm is measured with a USAF resolution target. Axially, an average height of 917.5 nm with a standard deviation of 49.9 nm is measured with a calibrated step height target of 925.5 nm.
  • Publication
    Secure and Privacy-Respecting Documentation for Interactive Manufacturing and Quality Assurance
    ( 2021)
    Wagner, Paul Georg
    ;
    Lengenfelder, Christian
    ;
    Holzbach, Gerrit
    ;
    Becker, Maximilian
    ;
    Birnstill, Pascal
    ;
    Voit, Michael
    ;
    Bejhad, Ali
    ;
    Samorei, Tom
    ;
    Beyerer, Jürgen
    The automated documentation of work steps is a requirement of many modern manufacturing processes. Especially when it comes to important procedures such as safety critical screw connections or weld seams, the correct and complete execution of certain manufacturing steps needs to be properly supervised, e.g., by capturing video snippets of the worker to be checked in hindsight. Without proper technical and organizational safeguards, such documentation data carries the potential for covert performance monitoring to the disadvantage of employees. Naïve documentation architectures interfere with data protection requirements, and thus cannot expect acceptance of employees. In this paper we outline use cases for automated documentation and describe an exemplary system architecture of a workflow recognition and documentation system. We derive privacy protection goals that we address with a suitable security architecture based on hybrid encryption, secret-sharing among multiple parties and remote attestation of the system to prevent manipulation. We finally contribute an outlook towards problems and possible solutions with regards to information that can leak through accessible metadata and with regard to more modular system architectures, where more sophisticated remote attestation approaches are needed to ensure the integrity of distributed components.
  • Publication
    ReS2tAC - UAV-borne real-time SGM stereo optimized for embedded ARM and CUDA devices
    ( 2021)
    Ruf, Boitumelo
    ;
    Mohrs, Jonas
    ;
    Weinmann, Martin
    ;
    Hinz, Stefan
    ;
    Beyerer, Jürgen
    With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased. For a long time, FPGAs were the only processing hardware that were capable of high-performance computing, while at the same time preserving a low power consumption, essential for embedded systems. However, the recently increasing availability of embedded GPU-based systems, such as the NVIDIA Jetson series, comprised of an ARM CPU and a NVIDIA Tegra GPU, allows for massively parallel embedded computing on graphics hardware. With this in mind, we propose an approach for real-time embedded stereo processing on ARM and CUDA-enabled devices, which is based on the popular and widely used Semi-Global Matching algorithm. In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs. We have evaluated our approach with different configurations on two public stereo benchmark datasets to demonstrate that they can reach an error rate as low as 3.3%. Furthermore, our experiments show that the fastest configuration of our approach reaches up to 46 FPS on VGA image resolution. Finally, in a use-case specific qualitative evaluation, we have evaluated the power consumption of our approach and deployed it on the DJI Manifold 2-G attached to a DJI Matrix 210v2 RTK unmanned aerial vehicle (UAV), demonstrating its suitability for real-time stereo processing onboard a UAV.
  • Publication
    An Occlusion-Aware Multi-Target Multi-Camera Tracking System
    ( 2021)
    Specker, Andreas
    ;
    Stadler, Daniel
    ;
    Florin, Lucas
    ;
    Beyerer, Jürgen
    Multi-camera tracking of vehicles on a city-scale level is a crucial task for efficient traffic monitoring. Most of the errors made by such multi-target multi-camera tracking systems arise due to tracking failures or misleading visual information of detection boxes under occlusion. Therefore, we propose an occlusion-aware approach that leverages temporal information from tracks to improve the single-camera tracking performance by an occlusion handling strategy and additional modules to filter false detections. For the multi-camera tracking, we discard obstacle-occluded detection boxes by a background filtering technique and boxes overlapping with other targets using the available track information to improve the quality of extracted visual features. Furthermore, topological and temporal constraints are incorporated to simplify the re-identification task in the multi-camera clustering. We give detailed insights into our method with ablative experiments and show its competitiveness on the CityFlowV2 dataset, where we achieve promising results ranking 4th in Track 3 of the 2021 AI City Challenge.
  • Publication
    Sensitivity enhanced roll-angle sensor by means of a quarter-waveplate
    ( 2021)
    Chen, Chia-Wei
    ;
    Hartrumpf, Matthias
    ;
    Längle, Thomas
    ;
    Beyerer, Jürgen
    Attitude metrology (roll, pitch, and yaw) playsan important role in many different fields. Roll angle is con-sidered the most difficult measurement quantity in angulardisplacements compared to pitch and yaw angles becausethe rotation axis of the roll angle is parallel to the probebeam. In this work, a sensitivity enhanced roll-angle sensor is presented. The principle is based on the polarizationchange of a sensing unit (quarter-waveplate). The polarization model is analyzed by Mueller matrix formalism. TheStokes parameters are detected by a Stokes polarimeter.The novel coaxial design improves the sensitivity and reduce the complexity of optical system alignment by meansof a fixed quarter-waveplate. The proposed sensor providesa simple setup to measure roll angles with a high sensitivity of 0.006∘ and a long unambiguous measurement range of 180∘.
  • Publication
    An Extended Modular Processing Pipeline for Event-Based Vision in Automatic Visual Inspection
    ( 2021)
    Beck, Moritz
    ;
    Maier, Georg
    ;
    Flitter, Merle
    ;
    Gruna, Robin
    ;
    Längle, Thomas
    ;
    Heizmann, Michael
    ;
    Beyerer, Jürgen
    Dynamic Vision Sensors differ from conventional cameras in that only intensity changes of individual pixels are perceived and transmitted as an asynchronous stream instead of an entire frame. The technology promises, among other things, high temporal resolution and low latencies and data rates. While such sensors currently enjoy much scientific attention, there are only little publications on practical applications. One field of application that has hardly been considered so far, yet potentially fits well with the sensor principle due to its special properties, is automatic visual inspection. In this paper, we evaluate current state-of-the-art processing algorithms in this new application domain. We further propose an algorithmic approach for the identification of ideal time windows within an event stream for object classification. For the evaluation of our method, we acquire two novel datasets that contain typical visual inspection scenarios, i.e., the inspection of objects on a conveyor belt and during free fall. The success of our algorithmic extension for data processing is demonstrated on the basis of these new datasets by showing that classification accuracy of current algorithms is highly increased. By making our new datasets publicly available, we intend to stimulate further research on application of Dynamic Vision Sensors in machine vision applications.