Junior-Professur Augmented Reality
Refine
Document Type
- Report (13)
- Article (5)
- Preprint (4)
- Part of a Book (2)
- Doctoral Thesis (2)
- Master's Thesis (1)
Institute
Keywords
- CGI <Computergraphik> (15)
- Maschinelles Sehen (12)
- Association for Computing Machinery / Special Interest Group on Graphics (9)
- Projektion (6)
- Handy (5)
- Neuronales Netz (5)
- Objekterkennung (5)
- Augmented Reality (4)
- Erweiterte Realität (4)
- Museum (4)
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.
Superimposing Dynamic Range
(2008)
Replacing a uniform illumination by a high-frequent illumination enhances the contrast of observed and captured images. We modulate spatially and temporally multiplexed (projected) light with reflective or transmissive matter to achieve high dynamic range visualizations of radiological images on printed paper or ePaper, and to boost the optical contrast of images viewed or imaged with light microscopes.
Superimposing Dynamic Range
(2009)
Replacing a uniform illumination by a high-frequent illumination enhances the contrast of observed and captured images. We modulate spatially and temporally multiplexed (projected) light with reflective or transmissive matter to achieve high dynamic range visualizations of radiological images on printed paper or ePaper, and to boost the optical contrast of images viewed or imaged with light microscopes.
CAMShift is a well-established and fundamental algorithm for kernel-based visual object tracking. While it performs well with objects that have a simple and constant appearance, it is not robust in more complex cases. As it solely relies on back projected probabilities it can fail in cases when the object's appearance changes (e.g. due to object or camera movement, or due to lighting changes), when similarly colored objects have to be re-detected or when they cross their trajectories. We propose extensions to CAMShift that address and resolve all of these problems. They allow the accumulation of multiple histograms to model more complex object appearance and the continuous monitoring of object identi- ties to handle ambiguous cases of partial or full occlusion. Most steps of our method are carried out on the GPU for achieving real-time tracking of multiple targets simultaneously. We explain an ecient GPU implementations of histogram generation, probability back projection, im- age moments computations, and histogram intersection. All of these techniques make full use of a GPU's high parallelization.
Visually impaired is a common problem for human life in the world wide. The projector-based AR technique has ability to change appearance of real object, and it can help to improve visibility for visually impaired. We propose a new framework for the appearance enhancement with the projector camera system that employed model predictive controller. This framework enables arbitrary image processing such as photo-retouch software in the real world and it helps to improve visibility for visually impaired. In this article, we show the appearance enhancement result of Peli's method and Wolffshon's method for the low vision, Jefferson's method for color vision deficiencies. Through experiment results, the potential of our method to enhance the appearance for visually impaired was confirmed as same as appearance enhancement for the digital image and television viewing.
Besides home entertainment and business presentations, video projectors are powerful tools for modulating images spatially as well as temporally. The re-evolving need for stereoscopic displays increases the demand for low-latency projectors and recent advances in LED technology also offer high modulation frequencies. Combining such high-frequency illumination modules with synchronized, fast cameras, makes it possible to develop specialized high-speed illumination systems for visual effects production. In this thesis we present different systems for using spatially as well as temporally modulated illumination in combination with a synchronized camera to simplify the requirements of standard digital video composition techniques for film and television productions and to offer new possibilities for visual effects generation. After an overview of the basic terminology and a summary of related methods, we discuss and give examples of how modulated light can be applied to a scene recording context to enable a variety of effects which cannot be realized using standard methods, such as virtual studio technology or chroma keying. We propose using high-frequency, synchronized illumination which, in addition to providing illumination, is modulated in terms of intensity and wavelength to encode technical information for visual effects generation. This is carried out in such a way that the technical components do not influence the final composite and are also not visible to observers on the film set. Using this approach we present a real-time flash keying system for the generation of perspectively correct augmented composites by projecting imperceptible markers for optical camera tracking. Furthermore, we present a system which enables the generation of various digital video compositing effects outside of completely controlled studio environments, such as virtual studios. A third temporal keying system is presented that aims to overcome the constraints of traditional chroma keying in terms of color spill and color dependency. ...
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.