Conference Paper

Using Self-Organizing Maps to Support Video Navigation

Otto-von-Guericke-Universität Magdeburg, Magdeburg, Saxony-Anhalt, Germany
DOI: 10.1007/11840817_42 Conference: ICANN (1)


Content-based video navigation is an efficient method for browsing video information. A common approach is to cluster shots
into groups and visualize them afterwards. In this paper, we present a prototype that follows in general this approach. Unlike
existing systems, the clustering is based on a growing self-organizing map algorithm. We focus on studying the applicability
of SOMs for video navigation support. We ignore the temporal aspect completely during the clustering, but we project the grouped
data on an original time bar control afterwards. This complements our interface by providing – at the same time – an integrated
view of time and content based information. The aim is to supply the user with as much information as possible on one single
screen, without overwhelming him. Special attention is also given to the interaction possibilities which are hierarchically

Full-text preview

Available from:
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: In this paper we present a variety of browsing interfaces for digital video information. The six interfaces are implemented on top of Físchlár, an operational recording, indexing, browsing and playback system for broadcast TV programmes. In developing the six browsing interfaces, we have been informed by the various dimensions which can be used to distinguish one interface from another. For this we include layeredness (the number of “layers” of abstraction which can be used in browsing a programme), the provision or omission of temporal information (varying from full timestamp information to nothing at all on time) and visualisation of spatial vs. temporal aspects of the video. After introducing and defining these dimensions we then locate some common browsing interfaces from the literature in this 3-dimensional “space” and then we locate our own six interfaces in this same space. We then present an outline of the interfaces and include some user feedback.
    Full-text · Chapter · Dec 1999
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: eo from a single camera running from camera on to camera off. Using one keyframe per shot means that representing a one-hour video usually requires hundreds of keyframes. In contrast, our approach for video indexing and summarization selects fewer keyframes that represent the entire video and index the interesting parts. The user can select the number of keyframes or the application can select the optimal number of keyframes based on display size, but a one-hour video typically will have between 10 and 40 keyframes. We use several techniques to present the automatically selected keyframes. A video directory listing shows one keyframe for each video and provides a slider that lets the user change the keyframes dynamically. The visual summary of a single video presents images in a compact, visually pleasing display. To deal with the large number of keyframes that represent clips in a video editing system, we group keyframes into piles based on their visual similarity. In all three inter
    Full-text · Article · Oct 2001 · Computer
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: This article describes the implementation of a system that is able to organize vast document collections according to textual similarities. It is based on the self-organizing map (SOM) algorithm. As the feature vectors for the documents statistical representations of their vocabularies are used. The main goal in our work has been to scale up the SOM algorithm to be able to deal with large amounts of high-dimensional data. In a practical experiment we mapped 6,840,568 patent abstracts onto a 1,002,240-node SOM. As the feature vectors we used 500-dimensional vectors of stochastic figures obtained as random projections of weighted word histograms.
    Full-text · Article · Feb 2000 · IEEE Transactions on Neural Networks
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: We report our experience with a novel approach to interactive information seeking that is grounded in the idea of summarizing query results through automated document clustering. We went through a complete system development and evaluation cycle: designing the algorithms and interface for our prototype, implementing them and testing with human users. Our prototype acted as an intermediate layer between the user and a commercial Internet search engine (AltaVista), thus allowing searches of the significant portion of World Wide Web. In our final evaluation, we processed data from 36 users and concluded that our prototype improved search performance over using the same search engine (AltaVista) directly. We also analyzed effects of various related demographic and task related parameters.
    Preview · Article · Nov 2001 · Information Processing & Management
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: A. Nürnberger (2001) has proposed a modification of the standard learning algorithm for self-organizing maps that iteratively increases the size of the map during the learning process by adding single neurons. The main advantage of this approach is the automatic control of the size and topology of the map, thus avoiding the problem of misclassification because of an imposed size. In this paper, we discuss how this algorithm can be used to visualize changes in data collections. We illustrate our approach with some examples
    Preview · Conference Paper · Feb 2002
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: The self-organizing map (SOM) is an efficient tool for visualization of multidimensional numerical data. In this paper, an overview and categorization of both old and new methods for the visualization of SOM is presented. The purpose is to give an idea of what kind of information can be acquired from different presentations and how the SOM can best be utilized in exploratory data visualization. Most of the presented methods can also be applied in the more general case of first making a vector quantization (e.g. k-means) and then a vector projection (e.g. Sammon's mapping).
    Preview · Article · Aug 1999 · Intelligent Data Analysis
  • Source
    [Show abstract] [Hide abstract] ABSTRACT: We have developed a novel system for content-based image retrieval in large, unannotated databases. The system is called PicSOM, and it is based on tree structured self-organizing maps (TS-SOMs). Given a set of reference images, PicSOM is able to retrieve another set of images which are similar to the given ones. Each TS-SOM is formed with a different image feature representation like color, texture, or shape. A new technique introduced in PicSOM facilitates automatic combination of responses from multiple TS-SOMs and their hierarchical levels. This mechanism adapts to the user's preferences in selecting which images resemble each other. Thus, the mechanism implements a relevance feedback technique on content-based image retrieval. The image queries are performed through the World Wide Web and the queries are iteratively refined as the system exposes more images to the user.
    Full-text · Article · Dec 2000 · Pattern Recognition Letters
Show more