Nemanja Lukic

Evaluation on the selection of video quality metrics for overall visual perception

Multimedia quality assessment has become an important issue for both monitoring and control of multimedia networks and for the optimization of the new algorithms for audiovisual enhancement. In this paper we evaluate various objective video quality metrics in respect to their match to the subjective assessment represented as mean opinion score (MOS). The proposed framework is aimed for low bit-rate MPEG-2 sequences in SD and HD format. We consider 29 objective measures for no-reference video quality assessment and rank them according to their match to the MOS independently and based on the cross-correlation between the objective measures. The selected set of ranked measures are incorporated into the proposed neural network scheme for estimating the overall visual perception. The selection of measures is done using the proposed linear model which aims at maximizing measure correlation to MOS and at the same time minimizing mutual correlation between the selected set of measures. The proposed VQA model is intended for (i) estimation of the overall visual quality and (ii) the evaluation of the objective video quality metrics for particular applications defined by the test sequences and corresponding visual perception results. We present the results of the proposed method on SD and HD sequences for different number of selected measures and provide comparison results (to the state-of-the-art methods) of the overall estimated quality.

Real-time video quality assessment platform

This paper presents a system for real-time video quality monitoring up to full-HD resolution in a networked environment. As sources of quality degradations, artifacts coming from block based compression are considered. The developed system captures live video, extracts video quality indicators in real-time, and renders them on the remote workstation.

A java API interface for the search of DTV services in embedded multimedia devices

The majority of DTV sets and set top boxes are embedded systems based on Linux. Utilizing network connectivity, they can provide many different kinds of information coming from the Internet such as news, sport events, weather and social networks through a large number of applications that are available for download. Considering the vast amount of data that is available to users, these platforms include specialized applications for unified search and presentation of this data. These applications currently do not support searching of data coming from DTV broadcast stream. This paper presents a proposal for the integration of data coming from DTV broadcast stream into a search mechanism on embedded systems which support the Java programming language. The proposal includes two parts: the Java API specification that is used to access DTV content from search applications, and the DTV native layer API. The latter is used to connect the native code to the Java API and includes approximate string matching technique for reducing spelling errors in search criterion.

Improving user experience with unique channel list on hybrid set-top boxes

This paper proposes novelty solution for creating unique channel list and channel source type selection in hybrid set-top box environment. The goal of this work is to simplify the usage of the set-top box for the user and to improve the TV watching experience. Improved user experience is achieved through automatically selecting best TV service by determining source type with best quality.

Real-time VP6 decoder optimization for MIPS based architectures

This paper describes the optimization of VP6 decoder for the MIPS based architectures. Programming languages C and inline assembler for the MIPS32 architecture were used. VP6 decoder with the main features is described, as well as MIPS processor and opportunities it offers. Profiling was performed for two data sets, and on the basis of these results optimization was performed using the vectorization. Finally, the execution time was measured for the decoder with data set, improvement for both test cases was obtained. Percentage of the consumption of the functions after optimization was calculated. The results were presented and analyzed.

Real-time wavelet based blur estimation on cell BE platform

We propose a real-time system for blur estimation using wavelet decomposition. The system is based on an emerging multi-core microprocessor architecture (Cell Broadband Engine, Cell BE) known to outperform any available general purpose or DSP processor in the domain of real-time advanced video processing solutions. We start from a recent wavelet domain blur estimation algorithm which uses histograms of a local regularity measure called average cone ratio (ACR). This approach has shown a very good potential for assessing the level of blur in the image yet some important aspects remain to be addressed in order for the method to become a practically working one. Some of these aspects are explored in our work. Furthermore, we develop an efficient real-time implementation of the novelty metric and integrate it into a system that captures live video. The proposed system estimates blur extent and renders the results to the remote user in real-time.

Software Based Video Improvement Implementation

This paper presents the evaluation of the programmable platforms regarding development and implementation of advanced real-time video improvement algorithms to be listed, as well as benchmark of such solutions vs. hardware implementations. Evaluation is done using video processing framework and implementation of the appropriate video algorithms on IBM Cell BE based platform.

Assessment of student satisfaction model: evidence of Western Balkans

In the midst of the growing changes in the higher education (HE) market, institutions of HE are more aware of their environment. Striving to maintain a position in an increasingly competitive HE market, they must continually deal with measuring and ensuring the satisfaction of its main customers – the students, as well their perceptions of service quality. The aim of this research was testing the proposed model of student satisfaction to determine the existence of the relationship between perceived service quality and student satisfaction, as well their impact on the student behavioural intentions. The survey involved 986 respondents – students from the Western Balkans. The model was tested by using the Structural Equation Modelling technique. Proposed model with minor modification achieved a good model fit, and the results confirmed previous research and provided further evidence that satisfaction and trust play a significant role in the relationship between perceived service quality and behavioural intentions.

Algorithms for making unified channel list on hybrid set-top boxes

This paper presents novel algorithms for unification of the channel list in hybrid set-top box environment. This environment is characterized by having multiple front-ends with different signal qualities for a single TV channel. Proposed algorithms improve users quality of experience by automatically choosing optimal channel list, combined from different TV front-ends, in a given environment

Improving teletext support for set top box based on Android operating system

This paper explains how to improve the implementation of teletext support. The aim is to enable content search teletext service through Android application for global search. Founded content needs to be highlighted while viewing a teletext page. Providing the content and teletext is carried by digital television signal receiver based on the Android operating system.