|
Evaluation of Methods for AR Coefficients Estimation Using Monte Carlo Analysis
Klejmova, Eva
Aim of this paper is to give recommendation for work with methods used for estimation of coefficients of autoregressive process. We applied Monte Carlo simulations to investigate performance of Burg, Yule-Walker and covariance methods. Evaluation of precision of spectral estimation is done with focus on signal length and lag order. The results are presented in graphical form and briefly discussed. Taking these results into account, Yule-Walker method shows better performance in case of long length signals and in case of overvalued lag order. Burg and covariance methods provide better results in case of short length signal and undervalued lag order.
|
|
Performance analysis of the newest video encoding standards
Klejmová, Eva ; Polák, Ladislav (referee) ; Slanina, Martin (advisor)
The aim of this work is to describe state-of-the-art high-definition video compression algorithms. The thesis focuses on the differences between algorithms and their functionality. Procedures for video sequences compression based on reference implementations of selected codecs are being proposed and their important parameters are being discussed. Bachelor's thesis deals with comparison of reference implementations based on subjective and objective video quality measurements and time requirements. The graphic interface for selected codecs has been also designed.
|
|
Analysis of spectral characteristics of signals
Sedláček, Matyáš ; Klejmová, Eva (referee) ; Poměnková, Jitka (advisor)
The subject of this bachelor’s thesis are the properties of power spectral density estimates, mainly how their properties depend on the analyzed signal’s parameters and the method being used. Important signal properties from the perspective of spectral analysis are defined, as well as measures for judging the estimate. Based on those, a choice of nonparametric and parametric spectral estimation methods is described. Analysis is performed on simulated signals and the results generalized into a set of recommendations for finding an estimate via an optimal method. These recommendations are then scrutinized and further discussed through estimation of real signal PSDs. Included is an application in MATLAB App Designer for generating spectral estimates and a collection of signals used.
|
|
Video Quality Measurement for HEVC
Klejmová, Eva ; Veřtát,, Ivo (referee) ; Slanina, Martin (advisor)
This diploma thesis deals with standard objective and subjective video quality assessments and with analysis of their applicability to HEVC. Also basic description of video compression standard H.265/HEVC is presented. The main focus of the thesis is a creation of the database of compressed video sequences. Important parameters and features of the reference encoder HM-12 are discussed. Selected methods of objective video quality assessments are implemented on the created database. A part of this thesis is also a suggestion of method for objective video quality assessment, application of this method and associated data collection. Final data is statistically analyzed and it’s correlation with objective tests is discussed.
|
|
Selected Aspects of Statistical Significance Testing in Time-Frequency Analysis
Klejmová, Eva ; Kohl,, Zdeněk (referee) ; Fidrmuc, Jarko (referee) ; Poměnková, Jitka (advisor)
Přeložená dizertační práce se zabývá analýzou a posouzením kvality odhadu frekvenční a časově-frekvenční transformace dat a formulaci doporučení pro práci s metodami. Při použití těchto metod vyvstává otázka, jak vyhodnotit, které složky spektrogramu jsou statisticky významné a které nikoli. V této práci analyzujeme vlastnosti standardních testů statistické významnosti. Diskutujeme o jejich výhodách a nevýhodách s ohledem na heteroskedastický charakter dat. Na základě našich experimentů jsou v práci navrženy dva typy testovacích metod, které snižují negativní aspekty standardních testů. Práce jen zakončena vytvořením rámce pro filtrování dat pomocí námi navržených metod.
|
|
Selected Aspects of Statistical Significance Testing in Time-Frequency Analysis
Klejmová, Eva ; Kohl,, Zdeněk (referee) ; Fidrmuc, Jarko (referee) ; Poměnková, Jitka (advisor)
Přeložená dizertační práce se zabývá analýzou a posouzením kvality odhadu frekvenční a časově-frekvenční transformace dat a formulaci doporučení pro práci s metodami. Při použití těchto metod vyvstává otázka, jak vyhodnotit, které složky spektrogramu jsou statisticky významné a které nikoli. V této práci analyzujeme vlastnosti standardních testů statistické významnosti. Diskutujeme o jejich výhodách a nevýhodách s ohledem na heteroskedastický charakter dat. Na základě našich experimentů jsou v práci navrženy dva typy testovacích metod, které snižují negativní aspekty standardních testů. Práce jen zakončena vytvořením rámce pro filtrování dat pomocí námi navržených metod.
|
|
Analysis of spectral characteristics of signals
Sedláček, Matyáš ; Klejmová, Eva (referee) ; Poměnková, Jitka (advisor)
The subject of this bachelor’s thesis are the properties of power spectral density estimates, mainly how their properties depend on the analyzed signal’s parameters and the method being used. Important signal properties from the perspective of spectral analysis are defined, as well as measures for judging the estimate. Based on those, a choice of nonparametric and parametric spectral estimation methods is described. Analysis is performed on simulated signals and the results generalized into a set of recommendations for finding an estimate via an optimal method. These recommendations are then scrutinized and further discussed through estimation of real signal PSDs. Included is an application in MATLAB App Designer for generating spectral estimates and a collection of signals used.
|
|
Evaluation of Methods for AR Coefficients Estimation Using Monte Carlo Analysis
Klejmova, Eva
Aim of this paper is to give recommendation for work with methods used for estimation of coefficients of autoregressive process. We applied Monte Carlo simulations to investigate performance of Burg, Yule-Walker and covariance methods. Evaluation of precision of spectral estimation is done with focus on signal length and lag order. The results are presented in graphical form and briefly discussed. Taking these results into account, Yule-Walker method shows better performance in case of long length signals and in case of overvalued lag order. Burg and covariance methods provide better results in case of short length signal and undervalued lag order.
|
|
Performance analysis of the newest video encoding standards
Klejmová, Eva ; Polák, Ladislav (referee) ; Slanina, Martin (advisor)
The aim of this work is to describe state-of-the-art high-definition video compression algorithms. The thesis focuses on the differences between algorithms and their functionality. Procedures for video sequences compression based on reference implementations of selected codecs are being proposed and their important parameters are being discussed. Bachelor's thesis deals with comparison of reference implementations based on subjective and objective video quality measurements and time requirements. The graphic interface for selected codecs has been also designed.
|
|
Video Quality Measurement for HEVC
Klejmová, Eva ; Veřtát,, Ivo (referee) ; Slanina, Martin (advisor)
This diploma thesis deals with standard objective and subjective video quality assessments and with analysis of their applicability to HEVC. Also basic description of video compression standard H.265/HEVC is presented. The main focus of the thesis is a creation of the database of compressed video sequences. Important parameters and features of the reference encoder HM-12 are discussed. Selected methods of objective video quality assessments are implemented on the created database. A part of this thesis is also a suggestion of method for objective video quality assessment, application of this method and associated data collection. Final data is statistically analyzed and it’s correlation with objective tests is discussed.
|