Content Classification of Multimedia Documents using Partitions of Low-Level Features

Audio-visual documents obtained from German TV news are classified according to the IPTC topic categorization scheme. To this end usual text classification techniques are adapted to speech, video, and non-speech audio. For each of the three modalities word analogues are generated: sequences of syllables for speech, “video words” based on low level color features (color moments, color correlogram and color wavelet), and “audio words” based on low-level spectral features (spectral envelope and spectral flatness) for non-speech audio. Such audio and video words provide a means to represent the different modalities in a uniform way. The frequencies of the word analogues represent audio-visual documents: the standard bag-of-words approach. Support vector machines are used for supervised classification in a 1 vs. n setting. Classification based on speech outperforms all other single modalities. Combining speech with non-speech audio improves classification. Classification is further improved by supplementing speech and non-speech audio with video words. Optimal F-scores range between 62% and 94% corresponding to 50% - 84% above chance. The optimal combination of modalities depends on the category to be recognized. The construction of audio and video words from low-level features provide a good basis for the integration of speech, non-speech audio and video.

System Architecture of a Mixed Reality Framework

In this paper the software architecture of a framework which simplifies the development of applications in the area of Virtual and Augmented Reality is presented. It is based on VRML/X3D to enable rendering of audio-visual information. We extended our VRML rendering system by a device management system that is based on the concept of a data-flow graph. The aim of the system is to create Mixed Reality (MR) applications simply by plugging together small prefabricated software components, instead of compiling monolithic C++ applications. The flexibility and the advantages of the presented framework are explained on the basis of an exemplary implementation of a classic Augmented Realityapplication and its extension to a collaborative remote expert scenario.

3-D Audio in Mobile Communication Devices: Methods for Mobile Head-Tracking

Future generations of mobile communication devices will serve more and more as multimedia platforms capable of reproducing high quality audio. In order to achieve a 3-D sound perception the reproduction quality of audio via headphones can be significantly increased by applying binaural technology. To be independent of individual head-related transfer functions (HRTFs) and to guarantee a good performance for all listeners, an adaptation of the synthesized sound field to the listener's head movements is required. In this article several methods of head-tracking for mobile communication devices are presented and compared. A system for testing the identified methods is set up and experiments are performed to evaluate the prosand cons of each method. The implementation of such a device in a 3-D audio system is described and applications making use of such a system are identified and discussed.

Visual Fixation for 3D Video Stabilization

Visual fixation is employed by humans and some animals to keep a specific 3D location at the center of the visual gaze. Inspired by this phenomenon in nature, this paper explores the idea to transfer this mechanism to the context of video stabilization for a handheld video camera. A novel approach is presented that stabilizes a video by fixating on automatically extracted 3D target points. This approach is different from existing automatic solutions that stabilize the video by smoothing. To determine the 3D target points, the recorded scene is analyzed with a stateof- the-art structure-from-motion algorithm, which estimates camera motion and reconstructs a 3D point cloud of the static scene objects. Special algorithms are presented that search either virtual or real 3D target points, which back-project close to the center of the image for as long a period of time as possible. The stabilization algorithm then transforms the original images of the sequence so that these 3D target points are kept exactly in the center of the image, which, in case of real 3D target points, produces a perfectly stable result at the image center. Furthermore, different methods of additional user interaction are investigated. It is shown that the stabilization process can easily be controlled and that it can be combined with state-of-theart tracking techniques in order to obtain a powerful image stabilization tool. The approach is evaluated on a variety of videos taken with a hand-held camera in natural scenes.