Post processing of multimedia information - concepts, problems, and techniques

Currently, most research work on multimedia information processing is focused on multimedia information storage and retrieval, especially indexing and content-based access of multimedia information. We consider multimedia information processing should include one more level-post-processing. Here "post-processing" means further processing of retrieved multimedia information, which includes fusion of multimedia information and reasoning with multimedia information to reach new conclusions. In this paper, the three levels of multimedia information processing storage, retrieval, and post-processing- are discussed. The concepts and problems of multimedia information post-processing are identified. Potential techniques that can be used in post-processing are suggested, By highlighting the problems in multimedia information post-processing, hopefully this paper will stimulate further research on this important but ignored topic.

Sensor fusion based missile guidance

In this paper we improve the guidance system performance via sensor fusion techniques. Vision based guidance systems can be improved in performance via radar tacking or employing video tracking by unmanned jying vehicles. We also introduce an image texture gradient based image segmentation technique to identify the target in a typical surface-to-air type application with the proposed Robust Extended Kalman Filter based state estimation technique for the implementation of the Proportional Navigation guidance controlleller.

The power of play-break for automatic detection and browsing of self-consumable sport video highlights

To enable content-based retrieval, highlights extraction from broadcasted sport video has been an active research topic in the last decade. There is a well-known theory that high-level semantic, such as goal in soccer can be detected based on the occurrences of specific audio and visual features that can be extracted automatically. However, there is yet a definitive solution for the scope (i.e. start and end) of the detection for self consumable highlights. Thus, in this paper we will primarily demonstrate the benefits of using play-break for this purpose. Moreover, we also propose a browsing scheme that is based on integrated play-break and highlights (extended from [1]). To validate our approach, we will present the results from some experiments and a user study.

Robust video/ultrasonic fusion based estimation for automotive applications

We describe how object estimation by a stationary or a non-stationary camera can be improved using recently-developed robust estimation ideas. The robustness of vision-based systems can be improved significantly by employing a Robust Extended Kalman Filter (REKF). The system performance is also enhanced by increasing the spatial diveristy in measurements via employing additional cameras for video capture. We describe a normal-flow based image segmentation technique to identify the object for the application of our proposed state estimation technique. Our simulations demonstrate that dynamic system modelling coupled with the application of a REKF significantly improves the estimation system performance, especially when large uncertainties are present.

Toward automatic extraction of expressive elements from motion pictures : tempo

This paper addresses the challenge of bridging the semantic gap that exists between the simplicity of features that can be currently computed in automated content indexing systems and the richness of semantics in user queries posed for media search and retrieval. It proposes a unique computational approach to extraction of expressive elements of motion pictures for deriving high-level semantics of stories portrayed, thus enabling rich video annotation and interpretation. This approach, motivated and directed by the existing cinematic conventions known as film grammar, as a first step toward demonstrating its effectiveness, uses the attributes of motion and shot length to define and compute a novel measure of tempo of a movie. Tempo flow plots are defined and derived for a number of full-length movies and edge analysis is performed leading to the extraction of dramatic story sections and events signaled by their unique tempo. The results confirm tempo as a useful high-level semantic construct in its own right and a promising component of others such as rhythm, tone or mood of a film. In addition to the development of this computable tempo measure, a study is conducted as to the usefulness of biasing it toward either of its constituents, namely, motion or shot length. Finally, a refinement is made to the shot length normalizing mechanism, driven by the peculiar characteristics of shot length distribution exhibited by movies. Results of these additional studies, and possible applications and limitations are discussed.

Computational media aesthetics: Finding meaning beautiful

Innovative media management, annotation, delivery, and navigation services will enrich online shopping, help-desk services, and anytime-anywhere training over wireless devices. However, the semantic gap between the rich meaning that users want when they query and browse media and the shallowness of the content descriptions that one can actually compute is weakening today's automatic content-annotation systems. To address such problems, an approach that markedly departs from existing methods based on detecting and annotating low-level audio-visual features is advocated.

Modelling multilevel data in multimedia : A hierarchical factor analysis approach

Multimedia content understanding research requires rigorous approach to deal with the complexity of the data. At the crux of this problem is the method to deal with multilevel data whose structure exists at multiple scales and across data sources. A common example is modeling tags jointly with images to improve retrieval, classification and tag recommendation. Associated contextual observation, such as metadata, is rich that can be exploited for content analysis. A major challenge is the need for a principal approach to systematically incorporate associated media with the primary data source of interest. Taking a factor modeling approach, we propose a framework that can discover low-dimensional structures for a primary data source together with other associated information. We cast this task as a subspace learning problem under the framework of Bayesian nonparametrics and thus the subspace dimensionality and the number of clusters are automatically learnt from data instead of setting these parameters a priori. Using Beta processes as the building block, we construct random measures in a hierarchical structure to generate multiple data sources and capture their shared statistical at the same time. The model parameters are inferred efficiently using a novel combination of Gibbs and slice sampling. We demonstrate the applicability of the proposed model in three applications: image retrieval, automatic tag recommendation and image classification. Experiments using two real-world datasets show that our approach outperforms various state-of-the-art related methods.

Robust digital image watermarking

This research presents a novel rank based image watermarking method and improved moment based and histogram based image watermarking methods. A high-frequency component modification step is also proposed to compensate the side effect of commonly used Gaussian pre-filtering. The proposed methods outperform the latest image watermarking methods.

Email categorization using multi-stage classification technique

This paper presents an innovative email categorization using a serialized multi-stage classification ensembles technique. Many approaches are used in practice for email categorization to control the menace of spam emails in different ways. Content-based email categorization employs filtering techniques using classification algorithms to learn to predict spam e-mails given a corpus of training e-mails. This process achieves a substantial performance with some amount of FP tradeoffs. It has been studied and investigated with different classification algorithms and found that the outputs of the classifiers vary from one classifier to another with same email corpora. In this paper we have proposed a multi-stage classification technique using different popular learning algorithms with an analyser which reduces the FP (false positive) problems substantially and increases classification accuracy compared to similar existing techniques.

Multi-level semantic analysis for sports video

There has been a huge increase in the utilization of video as one of the most preferred type of media due to its content richness for many significant applications including sports. To sustain an ongoing rapid growth of sports video, there is an emerging demand for a sophisticated content-based indexing system. Users recall video contents in a high-level abstraction while video is generally stored as an arbitrary sequence of audio-visual tracks. To bridge this gap, this paper will demonstrate the use of domain knowledge and characteristics to design the extraction of high-level concepts directly from audio-visual features. In particular, we propose a multi-level semantic analysis framework to optimize the sharing of domain characteristics.

A statistical-driven approach for automatic classification of events in AFL video highlights

Due to the repetitive and lengthy nature, automatic content-based summarization is essential to extract a more compact and interesting representation of sport video. State-of-the art approaches have confirmed that high-level semantic in sport video can be detected based on the occurrences of specific audio and visual features (also known as cinematic). However, most of them still rely heavily on manual investigation to construct the algorithms for highlight detection. Thus, the primary aim of this paper is to demonstrate how the statistics of cinematic features within play-break sequences can be used to less-subjectively construct highlight classification rules. To verify the effectiveness of our algorithms, we will present some experimental results using six AFL (Australian Football League) matches from different broadcasters. At this stage, we have successfully classified each play-break sequence into: goal, behind, mark, tackle, and non-highlight. These events are chosen since they are commonly used for broadcasted AFL highlights. The proposed algorithms have also been tested successfully with soccer video.

Extensible detection and indexing of highlight events in broadcasted sports video

Content-based indexing is fundamental to support and sustain the ongoing growth of broadcasted sports video. The main challenge is to design extensible frameworks to detect and index highlight events. This paper presents: 1) A statistical-driven event detection approach that utilizes a minimum amount of manual knowledge and is based on a universal scope-of-detection and audio-visual features; 2) A semi-schema-based indexing that combines the benefits of schema-based modeling to ensure that the video indexes are valid at all time without manual checking, and schema-less modeling to allow several passes of instantiation in which additional elements can be declared. To demonstrate the performance of the events detection, a large dataset of sport videos with a total of around 15 hours including soccer, basketball and Australian football is used.

Gustav Holst and British Music Society of Victoria collections at the State Library of Victoria

The paper presents a content-based evaluation, tracing the historical background of two heritage music collections at the State Library of Victoria (Melbourne, Australia).  In the case of the Gustav Holst and the British Music Society of Victoria Collections, history and content intertwine for the reason that both collections were initiated at the same time and by the same visionary power. During the early 1930s Louise Hanson-Dyer, a patron of Gustav Holst, issued a complete catalogue of the composer’s works and donated to the State Library of Victoria the first batch of Holst scores. This was to be the initial installment of a complete collection of published British music, which, however, was stopped due to duty tax complications. At the same time, the British Music Society of Victoria, founded by Louise Hanson-Dyer in 1921, maintained the first open library of chamber music in Australia. The BMS of Victoria Collection came to the State Library of Victoria in the 1980s. The most valuable materials in the collection are manuscripts of Australian twentieth century works, concert programs and first publications of British music from the 1920s and 1930s, which also supplement the Gustav Holst Collection. The collections are valuable reference and research collections, which document musical taste and music-making in Melbourne from 1920s well into the 1970s. The collections are also sources for studies into Louise Hanson-Dyer’s gift in collection development and her efforts to raise the professional standards of music performance in Melbourne and Australia.

MMM 2005 : proceedings of the 11th International Multimedia Modelling Conference : 12-14 January, 2005, Melbourne, Australia

The International Multimedia Modeling conference series is an annual forum to discuss the efficient representation, processing, interaction, integration, communication, and retrieval of multimedia information.
In particular, the 11th International Multimedia Modeling Conference (MMM2005) concentrates on common modeling frameworks for integrating the diverse fields of visual, audio, video, and virtual world information.
MMM2005 deals with emerging Multimedia Modeling topics that include:
• Audio Analysis and Modeling
• Video Manipulation and Modeling
• Video Mining and MPEG
• Image Modeling and Editing
• Image Retrieval
• Multimedia Presentation and Knowledge Sharing
• AI and Image Recognition
• Mobile and Virtual Multimedia Environments