Borko Furht

Neural Network Approach to Background Modeling for Video Object Segmentation

This paper presents a novel background modeling and subtraction approach for video object segmentation. A neural network (NN) architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed NN serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed NN is qualitatively and quantitatively examined and compared to two extant probabilistic object segmentation algorithms, based on a previously published test pool containing diverse surveillance-related sequences. The proposed algorithm is parallelized on a subpixel level and designed to enable efficient hardware implementation.

Multimedia systems: an overview

Advances in distributed multimedia systems have begun to significantly affect the development of on-demand multimedia services. Researchers are working within established computer areas to transform existing technologies and develop new ones. Multimedia is shown as the merging of computing, communications, and broadcasting.<<ETX>>

Design issues for interactive television systems

Computing, communication, and relevant standards are on the brink of enabling thousands of people to enjoy the services offered by large, distributed multimedia systems in their own homes. Collectively, these services will include TV (basic, subscription, and pay-per-view), service navigator, interactive entertainment, digital audio, video-on-demand, home shopping, financial transactions, interactive single- and multiuser games, digital multimedia libraries, and electronic versions of newspapers, magazines, TV program guides, and yellow pages. It is obvious that current TV systems and architectures must be redesigned to support such services. In this article, we propose potential solutions to modify existing systems to support these new functions, and we discuss related matters. >

Cloud Computing Fundamentals

In the introductory chapter we define the concept of cloud computing and cloud services, and we introduce layers and types of cloud computing. We discuss the differences between cloud computing and cloud services. New technologies that enabled cloud computing are presented next. We also discuss cloud computing features, standards, and security issues. We introduce the key cloud computing platforms, their vendors, and their offerings. We discuss cloud computing challenges and the future of cloud computing.

Augmented Reality: An Overview

We define Augmented Reality (AR) as a real-time direct or indirect view of a physical real-world environment that has been enhanced/augmented by adding virtual computer-generated information to it [1]. AR is both interactive and registered in 3D as well as combines real and virtual objects. Milgram’s Reality-Virtuality Continuum is defined by Paul Milgram and Fumio Kishino as a continuum that spans between the real environment and the virtual environment comprise Augmented Reality and Augmented Virtuality (AV) in between, where AR is closer to the real world and AV is closer to a pure virtual environment, as seen in Fig. 1.1 [2].

An adaptive real-time ECG compression algorithm with variable threshold

A real-time compression algorithm has been developed which is suitable for both real-time ECG (electrocardiogram) transmission and ECG data storing. The algorithm represents a modification of the amplitude zone time epoch coding (AZTEC) technique extended with several statistical parameters used to calculate the variable threshold. The proposed algorithm has been applied in the design of a pacemaker followup system for the online ECG data transmission from the pacemaker implanted in a human being to the computer system located at the clinic.<<ETX>>

A survey of multimedia content adaptation for mobile devices

With continued increase in the use of smartphones, user expectations of content access have also increased. Most of the content that exists today is not designed for mobile devices. Mobile devices cannot directly access most of the content due to the mismatch in device capability and content playback requirements. Content adaptation is an essential tool that bridges the gap between device capabilities and content formats. In this paper we present an overview of content adaptation and survey recent papers on content adaptation for mobile devices. We introduce the when, where, and what of content adaptation to help classify the content adaptation techniques and to select the appropriate techniques for a given content delivery environment.

Techniques for improving the capacity of video-on-demand systems

We present two techniques to improve the capacity of video on demand systems. Video on demand is an electronic video rental system in which clients request and play videos on-demand. Video on demand system can be implemented over an existing cable TV network or an upgraded ADSL network. The two techniques used to improve the capacity of video on-demand systems are segmentation and multicasting. Segmentation consists of dividing the video into several fixed length segments, and then transmitting the segments at regular intervals instead of transmitting the entire video continuously. Multicasting assumes that each subscriber has a limited storage space, so the same video segments can be multicast to subscribers simultaneously. Results of a comprehensive simulation study presented in the paper show a significant improvement in the capacity of the system when these two techniques are applied. In evaluating video on demand systems we considered the following parameters: the number of users supported, the number of videos played per day, and the number of requests rejected per day.

A study of transcoding on cloud environments for video content delivery

Media content distribution poses different challenges when it comes to supplying the variety of existing media formats requested by end-users. The need for an on demand transcoding stage may be justified under specific circumstances but is hampered by the high latency and long processing times. The great power cloud computing offers can be leveraged in a situation like this. This paper analyzes a use case where a Hadoop-based computer cloud is used as an aid in the transcoding of media content. The results point to the suitability of such a resource in a media distribution process requiring low cost streaming, such as the HTTP Live streaming scenario which supports streaming of audio or video to the iPhone, iPad, iPod touch and desktop computers as well as the transfer of video on demand with encryption and authentication.

A survey of multimedia compression techniques and standards. Part I: JPEG standard

Abstract This paper is the first part of a comprehensive survey of compression techniques and standards for multimedia applications. It covers the JPEG compression algorithm which is primarily used for full-color still image applications. The paper describes all the components of the JPEG algorithm including discrete cosine transform, quantization, and entropy encoding. It also describes both encoder and decoder architectures. The main emphasis is given to the sequential mode of operation which is the most typical use of JPEG compression; however, the other three modes of operation, progressive, lossless, and hierarchical JPEG, are described as well. A number of experimental data for both grayscale and color image compression is provided in the paper.