Refine
Year of publication
- 2020 (139) (remove)
Document Type
- Conference Proceeding (47)
- Article (36)
- Report (14)
- Part of a Book (12)
- Book (6)
- Other Publications (6)
- Doctoral Thesis (4)
- Master's Thesis (4)
- Journal (Complete Issue of a Journal) (4)
- Bachelor Thesis (3)
Keywords
- 3D ship detection (1)
- Accelerometers (1)
- Accessible Tourism (1)
- Actions (1)
- Adaptive (1)
- Adivasi (1)
- Agiles Lehren (1)
- Agiles Management (1)
- Apnoe (1)
- Architektur (1)
Institute
- Fakultät Architektur und Gestaltung (4)
- Fakultät Bauingenieurwesen (9)
- Fakultät Elektrotechnik und Informationstechnik (1)
- Fakultät Informatik (20)
- Fakultät Maschinenbau (5)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (13)
- Institut für Angewandte Forschung - IAF (4)
- Institut für Naturwissenschaften und Mathematik - INM (2)
- Institut für Optische Systeme - IOS (8)
- Institut für Strategische Innovation und Technologiemanagement - IST (10)
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the individual image-level predictions. Those methods take advantage of the uncertainty in the image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.
Mapping of tree seedlings is useful for tasks ranging from monitoring natural succession and regeneration to effective silvicultural management. Development of methods that are both accurate and cost-effective is especially important considering the dramatic increase in tree planting that is required globally to mitigate the impacts of climate change. The combination of high-resolution imagery from unmanned aerial vehicles and object detection by convolutional neural networks (CNNs) is one promising approach. However, unbiased assessments of these models and methods to integrate them into geospatial workflows are lacking. In this study, we present a method for rapid, large-scale mapping of young conifer seedlings using CNNs applied to RGB orthomosaic imagery. Importantly, we provide an unbiased assessment of model performance by using two well-characterised trial sites together containing over 30,000 seedlings to assemble datasets with a high level of completeness. Our results showed CNN-based models trained on two sites detected seedlings with sensitivities of 99.5% and 98.8%. False positives due to tall weeds at one site and naturally regenerating seedlings of the same species led to slightly lower precision of 98.5% and 96.7%. A model trained on examples from both sites had 99.4% sensitivity and precision of 97%, showing applicability across sites. Additional testing showed that the CNN model was able to detect 68.7% of obscured seedlings missed during the initial annotation of the imagery but present in the field data. Finally, we demonstrate the potential to use a form of weakly supervised training and a tile-based processing chain to enhance the accuracy and efficiency of CNNs applied to large, high-resolution orthomosaics.
Three-dimensional ship localization with only one camera is a challenging task due to the loss of depth information caused by perspective projection. In this paper, we propose a method to measure distances based on the assumption that ships lie on a flat surface. This assumption allows to recover depth from a single image using the principle of inverse perspective. For the 3D ship detection task, we use a hybrid approach that combines image detection with a convolutional neural network, camera geometry and inverse perspective. Furthermore, a novel calculation of object height is introduced. Experiments show that the monocular distance computation works well in comparison to a Velodyne lidar. Due to its robustness, this could be an easy-to-use baseline method for detection tasks in navigation systems.
Die Projektaufgabe bestand darin, den aktuellen Laborversuch zu modernisieren, indem die Kommunikation zwischen dem Versuchsaufbau und Laborrechner nicht wie bisher über Wandlerkarten stattfindet, sondern über EtherCAT und TwinCAT 3.
Die Installation von TwinCAT 3 mit den zugehörigen Erweiterungen und erforderlichen Programmen stellt sich als sehr umfangreich und schwierig dar, was die Installationsanleitungen zeigen. Außerdem gab es sehr viele Fehlerquellen, die nicht auf Anhieb ersichtlich waren, wie das Aktualisieren der aktuellen MATLAB Version. Ist die Installation abgeschlossen kann die Kommunikation zwischen MATLAB und TwinCAT relativ einfach umgesetzt werden.
In der Projektarbeit wurde anfangs dann die Kommunikation mit mehreren Tests überprüft und Optimierungen vorgenommen. So wurde zum Beispiel die Wegbegrenzung angepasst. Schwierigkeiten zeigten sich bei der Bedienung über MATLAB oder beim Abstürzen von MATLAB, da beim Stoppen oder Abstürzen von MATLAB, der zuletzt gesendete Wert immer noch an TwinCAT 3 anliegt und somit der Aktor weiter verfahren würde. Diese sehr gefährliche Situation wäre ein gravierender Nachteil, gegenüber der alten Kommunikation mit einer Wandlerkarte. Um einen sicheren Stopp zu garantieren, wird über ein neues TcCOM Objekt der Matlab-Status mit einem Togglebit überprüft, ändert sich der Wert des Bits nicht mehr, stoppt die Anlage sicher.
Um einen Vergleich mit dem bisherigen Masterversuch erhalten zu können, wurde die Strecke mit der neuen Kommunikation untersucht und ein passender Regler dafür auszulegt.
Die Auswertung der Impulsantwort sowie der „Spectrum-Analyse“ zeigten beim Vergleich mit den Schnittstellen gleiche Ergebnisse, somit sind die Versuche bei dem Laborversuch ohne Einschränkungen durchführbar. Die Auslegung des Reglers zeigte entgegen den Prognosen der Beckhoff-Experten sehr gute Ergebnisse und die Kommunikation über die Schnittstelle zeigte keine Probleme.
Einschränkungen zeigten sich jedoch bei der einzustellenden Abtastzeit, da eine Abtastzeit unter 2ms nicht möglich ist. Zwar kann man eine geringere Abtastzeit einstellen, jedoch zeigt sich bei der Auswertung, dass die Schnittstelle mit Abtastzeiten unter 2ms Probleme aufweist. Die Rechendauer wird deutlich größer und die größere Anzahl an Messpunkte kann nicht richtig verarbeitet werden. Ein Regler kann damit nicht implementiert werden.
Die Projektarbeit konnte somit erfolgreich angeschlossen werden und bis auf die aufwendige Installation sind die Erweiterungen von Beckhoff sehr zuverlässig und gut zu bedienen. Die ersten Voruntersuchen waren positiv, somit kann auch an weiteren Laborrechnern eine Umstellung der Schnittstelle in Betracht gezogen werden.
Creative industry and cultural tourism destination Lake Constance - a media discourse analysis
(2020)
The following media discourse analysis examines the news media coverage of four regional online newspapers, about the topics “creative industries” and “cultural tourism” at Lake Constance region in the period from 2006 until 2016. The results show that, besides event-relater reporting, there is currently no vibrant media discourse on the topics “creative industries” and “cultural tourism”. Even though the image of the Lake Constance region is heavily influenced by tourism, “cultural tourism” also plays a secondary role when it comes to regional news reporting. Moreover, discourses do not overlap and thus no synergies within the local media discourse are formed. This result is relevant for the regional tourism development, because the cooperation between “creative industries” and “cultural tourism” creates opportunities such as the expansion of the tourism offer and an extension of the tourist season. To activate unused opportunities at the different destinations of the region, a supra-regional visibility of the sector “creative industries” should be developed and the cooperation of the sector with local stakeholders of cultural tourism should be promoted.
This paper presents the goals, service design approach, and the results of the project “Accessible Tourism around Lake Constance”, which is currently run by different universities, industrial partners and selected hotels in Switzerland, Germany and Austria. In the 1st phase, interviews with different persons with disabilities and elderly persons have been conducted to identify the barriers and pains faced by tourists who want to spend their holidays in the region of Lake Constance as well as possible assistive technologies that help to overcome these barriers. The analysis of the interviews shows that one third of the pains and barriers are due to missing, insufficient, wrong or inaccessible information about the
accessibility of the accommodation, surroundings, and points of interests during the planning phase of the holidays. Digital assistive technologies hence play a
major role in bridging this information gap. In the 2nd phase so-called Hotel-Living-Labs (HLL) have been established where the identified assistive technologies
can be evaluated. Based on these HLLs an overall service for accessible holidays has been designed and developed. In the last phase, this service has been implemented
based on the HLLs as well as the identified assistive technologies and is currently field tested with tourists with disabilities from the three participated countries.
Philosophie & Rhetorik
(2020)
Digital technology and architecture have become inseparable, with new approaches and methodologies not just affecting the workflows and practice of architects but shaping the very character of architecture.
This compendious work offers a wide-ranging orientation to the new landscape with its opportunities, its challenges, and its vast potential.
Shared Field, Divided Field
(2020)