Catálogo de publicaciones - libros

Video summarization approaches have various fields of application, specifically related to organizing, browsing and accessing large video databases. In this paper we propose and evaluate two novel approaches for video summarization, one based on spectral methods and the other on ant-tree clustering. The overall summary creation process is broke down in two steps: detection of similar scenes and extraction of the most representative ones. While clustering approaches are used for scene segmentation, the post-processing logic merges video scenes into a subset of user relevant scenes. In the case of the spectral approach, representative scenes are extracted following the logic that important parts of the video are related with high motion activity of segments within scenes. In the alternative approach we estimate a subset of relevant video scene using ant-tree optimization approaches and in a supervised scenario certain scenes of no interest to the user are recognized and excluded from the summary. An experimental evaluation validating the feasibility and the robustness of these approaches is presented.

The paper is devoted to the development of an ontology of the domain “Image processing, analysis, recognition, and understanding” based on the existing image analysis thesaurus. Such an ontology could be used to support a wide range of tasks, including automated image analysis, algorithmic knowledge reuse, intelligent information retrieval, etc. Main steps and first results of the ontology development process are described.

Medical images coming from different sources can often provide different information. So, combining two or more co-registered multimodal medical images into a single image (image fusion) is an important support to the medical diagnosis. Most of the used image fusion techniques are based on the Multiresolution Analysis (MRA), which is able to decompose an image into several components at different scales. This paper presents a novel Wavelet-based method to fuse medical images according to the MRA approach, that aims to put the right “semantic” content in the fused image by applying two different quality indexes: variance and modulus maxima. Experimental tests show very encouraging results in terms of both quantitative and qualitative evaluations.

Multiresolution analysis (MRA) and component substitution (CS) are the two basic frameworks to which image fusion algorithms can be reported when merging multi-spectral (MS) and panchromatic (Pan) images (Pan-sharpening). State-of-the-art algorithms add spatial details derived from the Pan image to the MS bands according to an injection model. The capability of the model to describe the relationship between the MS and Pan images is crucial for the quality of fusion results. Although context adaptive (CA) injection models have been proposed in the framework of MRA, their adoption in CS schemes has been scarcely investigated so far. In this work a CA injection model already tested for MRA algorithms is evaluated also for CS schemes. Qualitative and quantitative results reported for IKONOS high spatial resolution data show that CA injection models are more efficient than global ones.

In this paper we describe the main aspects of a system to perform non-trivial segmentations of 3D surface meshes and to annotate the detected parts through concepts expressed by an ontology. Each part is connected to an instance in a knowledge base to ease the retrieval process in a semantics-based context. Through an intuitive interface, users create such instances by simply selecting proper classes in the ontology; attributes and relations with other instances can be computed automatically based on a customizable analysis of the underlying topology and geometry of the parts.

We describe a 3D shape classification framework, and discuss the performance of selective and creative prototypes extracted from structural descriptors.

This paper presents a group of post-processing techniques aimed to on-line adaptive video summary generation based on video analysis curves, named relevance curves obtained by different approaches (e.g., extraction of visual features, semantic features, rate-distortion curves). The developed techniques can be applied to improve the quality of the generated video summaries, control the summaries length and constitute a way to generate summaries with independence of the approach taken to generate the relevance curves that are used as basis for summary generation.

Multimodal and dialogue-based mobile interfaces to the Semantic Web offer access to complex knowledge and information structures. We explore more fine-grained co-ordination of multimodal presentations in mobile environments by graph visualisations and navigation in ontological RDF result structures and multimedia archives. Semantic Navigation employs integrated ontology structures and leverages graphical user interface activity for dialogical interaction on mobile devices. Hence information visualisation benefits from the Semantic Web. Constraint-based programming helps to find optimised multimedia graph visualisations. We report on the constraint-formulisation process to optimise the visualisation of semantic-based information on small devices and its integration in a distributed dialogue system.

Presentation of content is an important aspect of today’s virtual reality applications, especially in domains such as virtual exhibitions. The large amount and variety of exhibits in such applications raise a need for adaptation and personalization of the environment. This paper presents a content personalization framework for Virtual Exhibitions, which is based on a semantic description of content and on information implicitly collected about the users through their interaction. The proposed framework uses stereotypes to initialize user models, adapts user profiles dynamically and clusters users into interest groups. A 3D virtual museum has been implemented as a case study, and an evaluation has been conducted.

Music is much more than passive listening to a binary file. It can easily become a , the , of and . Music has always incorporated the newest technology of a given epoch, and the marriage with computer science is at least as old as the early attempts by and . For at least forty centuries in all cultures, music has used to represent its contents and give hints for its performance, thus this standard is the continuation of this tradition with its use of . This article illustrates the possibilities offered by the new standard IEEE P1599, locally known as project MX, through a few meant to show its flexibility and its role as .