54.72 Künstliche Intelligenz
Refine
Document Type
- Article (6)
- Doctoral Thesis (5)
- Report (3)
Institute
- Junior-Professur Augmented Reality (6)
- Institut für Strukturmechanik (ISM) (2)
- In Zusammenarbeit mit der Bauhaus-Universität Weimar (1)
- Professur Content Management und Webtechnologien (1)
- Professur Informatik im Bauwesen (1)
- Professur Informatik in der Architektur (1)
- Professur Informations- und Wissensverarbeitung (1)
- Professur Theorie und Geschichte der modernen Architektur (1)
Keywords
- Handy (4)
- Museumsführer (4)
- Neuronales Netz (4)
- Objekterkennung (4)
- Anpassung (3)
- Museum (3)
- museum guidance (3)
- object recognition (3)
- Bilderkennung (2)
- Maschinelles Lernen (2)
Das Ziel dieser Arbeit war es, durch Verwendung geeigneter vorhandener CAD-Pläne die Bearbeitung neuer CAD-Pläne zu unterstützen. Entstanden ist ein generischer Ansatz zum fallbasierten Schließens. Da in CAD-Plänen die räumliche Struktur eine wichtige Rolle spielt, ist das Konzept auf strukturorientierte Anwendungen ausgerichtet. Deshalb bezeichne ich es als ein Konzept zum " strukturorientierten fallbasierten Schließen". Die Arbeit spezifiziert das Minimum an Wissen, welches zur Suche und Wiederverwendung von Fällen benötigt wird, wie das darüber hinausgehende Wissen verarbeitet wird, welche Zusammenhänge es zum Beispiel zwischen Vergleichs- und Anpassungswissen gibt und wie man das Wissen modellieren kann. Zur Erläuterung wird das benötigte Wissen anhand verschiedener Anwendungen dargestellt. Das in der Arbeit vorgestellte Konzept erlaubt die Ergänzung, Detaillierung und Korrektur einer Anfrage. Die beiden entscheidenden Algorithmen dienen dem Vergleich von Anfrage und Fall und der Anpassung der Information des Falles zur Modifikation der Anfrage.
Gegenstand der vorliegenden Arbeit ist die Konzeption und prototypische Umsetzung von Techniken des Computer Supported Cooperative Work (CSCW) im Rahmen einer integrierten objektorientierten und dynamischen Bauwerksmodellverwaltung zur Unterstützung der Bauwerksplanung. Die Planung von Bauwerken ist durch einen hohen Grad an Arbeitsteiligkeit, aber auch durch eine schwache Strukturierung der ablaufenden Prozesse gekennzeichnet. Besonders durch den Unikatcharakter des Planungsgegenstands \'Bauwerk\' ergeben sich signifikante Unterschiede zum Entwurf anderer, durch Serienfertigung produzierter Industriegüter. Zunehmend wird die Planung von Bauwerken in Virtual Enterprises ausgeführt, die sich durch eine dynamische Organisationsstruktur, geographische Verteilung der Partner, schwer normierbare Informationsflüsse und eine häufig stark heterogene informationstechnische Infrastruktur auszeichnen. Zur rechnerinternen Repräsent! ation des Planungsgegenstands haben sich objektorientierte Bauwerksmodelle bewährt. Aufgrund der Veränderlichkeit der Bauwerke und deren rechnerinterner Repräsentation im Laufe des Bauwerkslebenszyklus ist eine dynamische Anpassung der Modelle unumgänglich. Derartige in Form von Taxonomien dargestellte dynamische Bauwerksmodellstrukturen können gemeinsam mit den in Instanzform vorliegenden konkreten Projektinformationen in entsprechenden Modellverwaltungssystemen (MVS) gehandhabt werden. Dabei wird aufgrund der Spezialisierung und Arbeitsteilung im Planungsprozess von einer inhaltlich verknüpften Partialmodellstruktur, die räumlich verteilt sein kann, ausgegangen. Die vorgeschlagenen Methoden zur Koordinierung der Teamarbeit in der Bauwerksplanung beruhen auf der Nutzung von CSCW–Techniken für \'Gemeinsame Informationsräume\' und \'Workgroup Computing\', die im Kontext der als Integrationsbasis fungierenden Modellverwaltungssysteme umgesetzt werden. Dazu werden die zur d! ynamischen Bauwerksmodellierung erforderlichen Metaebenenfunk! tionalitäten sowie Ansätze zur Implementierung von Modellverwaltungskernen systematisiert. Ebenso werden notwendige Basistechniken für die Realisierung von MVS untersucht und eine Architektur zur rollenspezifischen Präsentation dynamischer Modellinhalte vorgestellt. Da klassische Schichtenmodelle nicht auf die Verhältnisse in Virtual Enterprises angewendet werden können, wird eine physische Systemarchitektur mit einem zentralen Projektserver, Domänenservern und Domänenclients vorgestellt. Ebenso werden Techniken zur Sicherung des autorisierten Zugriffs sowie des Dokumentencharakters beschrieben. Zur Unterstützung der asynchronen Phasen der Kooperation wird der gemeinsame Informationsraum durch Mappingtechniken zur Propagation und Notifikation von Änderungsdaten bezüglich relevanter Modellinformationen ergänzt. Zur Unterstützung synchroner Phasen werden Techniken zur Schaffung eines gemeinsamen Kontexts durch relaxierte WYSIWIS–Präsentationen auf Basis der Modellinformationen! verbunden mit Telepresence–Techniken vorgestellt. Weiterhin werden Methoden zur Sicherung der Group–Awareness für alle Kooperationsphasen betrachtet.
We present PhoneGuide – an enhanced museum guidance approach that uses camera-equipped mobile phones and on-device object recognition. Our main technical achievement is a simple and light-weight object recognition approach that is realized with single-layer perceptron neuronal networks. In contrast to related systems which perform computational intensive image processing tasks on remote servers, our intention is to carry out all computations directly on the phone. This ensures little or even no network traffic and consequently decreases cost for online times. Our laboratory experiments and field surveys have shown that photographed museum exhibits can be recognized with a probability of over 90%. We have evaluated different feature sets to optimize the recognition rate and performance. Our experiments revealed that normalized color features are most effective for our method. Choosing such a feature set allows recognizing an object below one second on up-to-date phones. The amount of data that is required for differentiating 50 objects from multiple perspectives is less than 6KBytes.
Although audio guides are widely established in many museums, they suffer from several drawbacks compared to state-of-the-art multimedia technologies: First, they provide only audible information to museum visitors, while other forms of media presentation, such as reading text or video could be beneficial for museum guidance tasks. Second, they are not very intuitive. Reference numbers have to be manually keyed in by the visitor before information about the exhibit is provided. These numbers are either displayed on visible tags that are located near the exhibited objects, or are printed in brochures that have to be carried. Third, offering mobile guidance equipment to visitors leads to acquisition and maintenance costs that have to be covered by the museum. With our project PhoneGuide we aim at solving these problems by enabling the application of conventional camera-equipped mobile phones for museum guidance purposes. The advantages are obvious: First, today’s off-the-shelf mobile phones offer a rich pallet of multimedia functionalities ---ranging from audio (over speaker or head-set) and video (graphics, images, movies) to simple tactile feedback (vibration). Second, integrated cameras, improvements in processor performance and more memory space enable supporting advanced computer vision algorithms. Instead of keying in reference numbers, objects can be recognized automatically by taking non-persistent photographs of them. This is more intuitive and saves museum curators from distributing and maintaining a large number of physical (visible or invisible) tags. Together with a few sensor-equipped reference tags only, computer vision based object recognition allows for the classification of single objects; whereas overlapping signal ranges of object-distinct active tags (such as RFID) would prevent the identification of individuals that are grouped closely together. Third, since we assume that museum visitors will be able to use their own devices, the acquisition and maintenance cost for museum-owned devices decreases.
We present an enhancement towards adaptive video training for PhoneGuide, a digital museum guidance system for ordinary camera–equipped mobile phones. It enables museum visitors to identify exhibits by capturing photos of them. In this article, a combined solution of object recognition and pervasive tracking is extended to a client–server–system for improving data acquisition and for supporting scale–invariant object recognition.
In this paper, we present a novel technique for adapting local image classifiers that are applied for object recognition on mobile phones through ad-hoc network communication between the devices. By continuously accumulating and exchanging collected user feedback among devices that are located within signal range, we show that our approach improves the overall classification rate and adapts to dynamic changes quickly. This technique is applied in the context of PhoneGuide – a mobile phone based museum guidance framework that combines pervasive tracking and local object recognition for identifying a large number of objects in uncontrolled museum environments.
We present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relationships among the subobjects to verify and to predict locations of detected and undetected subobjects, respectively. By continuously refining the spatial relationships throughout the detection process, even locations of completely occluded exhibits can be determined. Finally, all detected subobjects are labeled and the user can select the object of interest for retrieving corresponding multimedia information. This approach is applied in the context of PhoneGuide, an adaptive museum guidance system for camera-equipped mobile phones. We show that the recognition of subobjects using spatial relationships is up to 68% faster than related approaches without spatial relationships. Results of a field experiment in a local museum illustrate that unexperienced users reach an average recognition rate for subobjects of 85.6% under realistic conditions.
The advent of high-performance mobile phones has opened up the opportunity to develop new context-aware applications for everyday life. In particular, applications for context-aware information retrieval in conjunction with image-based object recognition have become a focal area of recent research. In this thesis we introduce an adaptive mobile museum guidance system that allows visitors in a museum to identify exhibits by taking a picture with their mobile phone. Besides approaches to object recognition, we present different adaptation techniques that improve classification performance. After providing a comprehensive background of context-aware mobile information systems in general, we present an on-device object recognition algorithm and show how its classification performance can be improved by capturing multiple images of a single exhibit. To accomplish this, we combine the classification results of the individual pictures and consider the perspective relations among the retrieved database images. In order to identify multiple exhibits in pictures we present an approach that uses the spatial relationships among the objects in images. They make it possible to infer and validate the locations of undetected objects relative to the detected ones and additionally improve classification performance. To cope with environmental influences, we introduce an adaptation technique that establishes ad-hoc wireless networks among the visitors’ mobile devices to exchange classification data. This ensures constant classification rates under varying illumination levels and changing object placement. Finally, in addition to localization using RF-technology, we present an adaptation technique that uses user-generated spatio-temporal pathway data for person movement prediction. Based on the history of previously visited exhibits, the algorithm determines possible future locations and incorporates these predictions into the object classification process. This increases classification performance and offers benefits comparable to traditional localization approaches but without the need for additional hardware. Through multiple field studies and laboratory experiments we demonstrate the benefits of each approach and show how they influence the overall classification rate.
Many researchers are working on developing robots into adequate partners, be it at the working place, be it at home or in leisure activities, or enabling elder persons to lead a self-determined, independent life. While quite some progress has been made in e.g. speech or emotion understanding, processing and expressing, the relations between humans and robots are usually only short-term. In order to build long-term, i.e. social relations, qualities like empathy, trust building, dependability, non-patronizing, and others will be required. But these are just terms and as such no adequate starting points to “program” these capacities even more how to avoid the problems and pitfalls in interactions between humans and robots. However, a rich source for doing this is available, unused until now for this purpose: artistic productions, namely literature, theater plays, not to forget operas, and films with their multitude of examples. Poets, writers, dramatists, screen-writers, etc. have studied for centuries the facets of interactions between persons, their dynamics, and the related snags. And since we wish for human-robot relations as master-servant relations - the human obviously being the master - the study of these relations will be prominent. A procedure is proposed, with four consecutive steps, namely Selection, Analysis, Categorization, and Integration. Only if we succeed in developing robots which are seen as servants we will be successful in supporting and helping humans through robots.