Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters
4
4
Reset filters

Settings
Now showing 1 - 4 of 4
No Thumbnail Available
Publication

Making Object Detection Available to Everyone - A Hardware Prototype for Semi-automatic Synthetic Data Generation

2020 , Besginow, Andreas , Büttner, Sebastian , Röcker, Carsten

The capabilities of object detection are well known, but many projects don't use them, despite potential benefit. Even though the use of object detection algorithms is facilitated through frameworks and publications, a big issue is the creation of the necessary training data. To tackle this issue, this work shows the design and evaluation of a prototype, which allows users to create synthetic datasets for object detection in images. The prototype is evaluated using YOLOv3 as the underlying detector and shows that the generated datasets are equally good in quality as manually created data. This encourages a wide adoption of object detection algorithms in different areas, since image creation and labeling is often the most time consuming step.

View
No Thumbnail Available
Publication

Dimensionality Reduction and Anomaly Detection for CPPS Data using Autoencoder

2019 , Eiteneuer, Benedikt , Hranisavljevic, Nemanja , Niggemann, Oliver

Unsupervised anomaly detection (AD) is a major topic in the field of Cyber-Physical Production Systems (CPPSs). A closely related concern is dimensionality reduction (DR) which is: 1) often used as a preprocessing step in an AD solution, 2) a sort of AD, if a measure of observation conformity to the learned data manifold is provided. We argue that the two aspects can be complementary in a CPPS anomaly detection solution. In this work, we focus on the nonlinear autoencoder (AE) as a DR/AD approach. The contribution of this work is: 1) we examine the suitability of AE reconstruction error as an AD decision criterion in CPPS data. 2) we analyze its relation to a potential second-phase AD approach in the AE latent space 3) we evaluate the performance of the approach on three real-world datasets. Moreover, the approach outperforms state-of-the-art techniques, alongside a relatively simple and straightforward application.

View
No Thumbnail Available
Publication

Network Slicing. An Industry Perspective

2019 , Ansah, Frimpong , Majumder, Mainak , Meer, Hermann de , Jasperneite, Jürgen

The prevalence of the term ""Network Slicing"" in today's communication network research community signifies the concept worthy of focus. However, despite its ubiquitous usage, there are varied interpretations of the concept which often leads to disagreement and confusion. The root of this misunderstanding lies in what the term ""Slicing"" means to the user and the context of its application. Network slicing has been considered as a key concept in 5G which will enable various types of services like enhanced Mobile Broadband (eMBB), Ultra Low Latency Reliable Communication (URLLC) and massive Machine Type Communication (mMTC) for industries. Despite all the standardization efforts, less progress has happened in the field to demystify the concept due to the misinterpretation of the term by various parties. As a result, this paper aims to provide an industrial perspective on the concept of Slicing and its usage in industrial communication networks. It shall as well propose contextualized taxonomy of the areas of usage as a way of reducing the vagueness surrounding the concept. Thus, within this context, an objective rather than subjective comprehension can ensue in intellectual discussions.

View
No Thumbnail Available
Publication

Utilization of the Asset Administration Shell to Support Humans During the Maintenance Process

2019 , Lang, Dorota , Grunau, Sergej , Wisniewski, Lukasz , Jasperneite, Jürgen

Maintenance is an important set of various activities related to preserving from failure or decline. Improper or lack of maintenance may result in excessive component wear, production quality deterioration, or even longer downtime. However, today's production facilities strive to devote the least amount of necessary maintenance time in order to maximize production time. Therefore, new solutions for deliberate and efficient maintenance are needed. The solution proposed in this paper benefits from the newest trends and innovations in industry, namely the Asset Administration Shell (AAS) which is part of the Industrie 4.0 (I4.0) concept. The AAS shall contain the maintenance submodel which shall be used for supporting humans during the maintenance process. The submodel provides a standardized description of required tools and parts as well as step-by-step instructions which also include safety concerns and multimedia files, such as pictures and videos. In this way, maintenance can be carried out more reliably, resulting in reduced downtime. In addition, feedback from the maintenance process shall be stored in the submodel and fed through an I4.0-compliant network to other processes from different phases of the life cycle in order to improve them.

View