Refine
H-BRS Bibliography
- no (36) (remove)
Departments, institutes and facilities
Document Type
- Doctoral Thesis (36) (remove)
Year of publication
Has Fulltext
- no (36)
Keywords
- Deutschland (2)
- Produktionstheorie (2)
- Business Ethnography (1)
- Differentielle Kryptoanalyse (1)
- Dreidimensionales maschinelles Sehen (1)
- Eingebettetes System (1)
- Einkommen (1)
- Einkommenshpyothese (1)
- Enhancer (1)
- Fehlerbehandlung (1)
Zumutbarkeit von Arbeit
(1992)
Die vorwiegend empiristische Analyse der sozialistischen Staaten führt bei der Beurteilung ihrer Steuerungsprobleme oft zu ideologisch durchsetzten ad-hoc Hypothesen. Mit der vorliegenden Arbeit wird hingegen der Versuch unternommen, Entstehung, Folgen und Bewältigung dieser Probleme einer systematischen Erklärung näher zu bringen.
This dissertation presents a probabilistic state estimation framework for integrating data-driven machine learning models and a deformable facial shape model in order to estimate continuous-valued intensities of 22 different facial muscle movements, known as Action Units (AU), defined in the Facial Action Coding System (FACS). A practical approach is proposed and validated for integrating class-wise probability scores from machine learning models within a Gaussian state estimation framework. Furthermore, driven mass-spring-damper models are applied for modelling the dynamics of facial muscle movements. Both facial shape and appearance information are used for estimating AU intensities, making it a hybrid approach. Several features are designed and explored to help the probabilistic framework to deal with multiple challenges involved in automatic AU detection. The proposed AU intensity estimation method and its features are evaluated quantitatively and qualitatively using three different datasets containing either spontaneous or acted facial expressions with AU annotations. The proposed method produced temporally smoother estimates that facilitate a fine-grained analysis of facial expressions. It also performed reasonably well, even though it simultaneously estimates intensities of 22 AUs, some of which are subtle in expression or resemble each other closely. The estimated AU intensities tended to the lower range of values, and were often accompanied by a small delay in onset. This shows that the proposed method is conservative. In order to further improve performance, state-of-the-art machine learning approaches for AU detection could be integrated within the proposed probabilistic AU intensity estimation framework.
Multi-hop Netze sind seit vielen Jahren Forschungsthema. Seit einigen Jahren gibt es auch erste Realisierungen solcher Netze. Sie ermöglichen es, ohne feste Infrastruktur sich selbst organisierende Netze zu realisieren. Dies macht sie für vielfältige zivile wie taktische Szenarien interessant. In der vorliegenden Arbeit liegt der Fokus auf taktischen Szenarien, wie Szenarien der öffentlichen Sicherheit, militärischen oder Katastrophenszenarien. In solchen Szenarien kann für die Kommunikation auf der letzten Meile nicht von existierender Kommunikationsinfrastruktur ausgegangen werden. Taktische multi-hop Netze stellen eine Möglichkeit dar, die Kommunikation auf der letzen Meile trotzdem zu realisieren.
The topic of this PhD project is in the context of cross-reality, a term that defines mixed reality environments that tunnel dense real-world data acquired through the use of sensor/actuator device networks into virtual worlds. It is part of the ongoing academia and industry efforts to achieve interoperability between virtual and real devices and services.