Researcher:
Akyol, Emrah

Profile Picture
ORCID

Job Title

Master Student

First Name

Emrah

Last Name

Akyol

Name

Name Variants

Akyol, Emrah

Email Address

Birth Date

Filters

2004 - 20058

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.269556dd-8873-4815-a982-201d0da1aad7

Search Results

Now showing 1 - 8 of 8
  • Placeholder
    PublicationMetadata only
    Robust speech recognition using adaptively denoised wavelet coefficients
    (IEEE, 2004) Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; N/A; Tekalp, Ahmet Murat; Erzin, Engin; Akyol, Emrah; Faculty Member; Faculty Member; Master Student; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; 26207; 34503; N/A
    The existence of additive noise affects the performance of speech recognition in real environments. We propose a new set of feature vectors for robust speech recognition using denoised wavelet coefficients. The use of wavelet coefficients in speech processing is motivated by the ability of the wavelet transform to capture both time and frequency information and the non-stationary behaviour of speech signals. We use one set of noisy data, such as data with car noise, and we use hard thresholding in the best basis for denoising. We use isolated digits as our database in our HMM based speech recognition system. A performance comparison of hard thresholding denoised wavelet coefficients and MFCC feature vectors is presented.
  • Placeholder
    PublicationMetadata only
    Scalable multiple description video coding with flexible number of descriptions
    (IEEE, 2005) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Akyol, Emrah; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Master Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 26207; 16372
    Multiple description video coding mitigates the effects of packet losses introduced by congestion and/or bit errors. in this paper, we propose a novel multiple description video coding technique, based on fully scalable wavelet video coding, which allows post encoding adaptation of the number of descriptions, the redundancy level of each description, and bitrate of each description by manipulation of the encoded bitstream. We demonstrate that the proposed method provides excellent coding efficiency, outperforming most other multiple description methods proposed so far. We also provide experimental results to show that varying the number of descriptions according to network conditions is superior to using a fixed number of descriptions, by means of NS-2 network simulation of a peer-to-peer video streaming system.
  • Placeholder
    PublicationMetadata only
    Motion-compensated temporal filtering within the H.264/AVC standard
    (IEEE, 2004) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Akyol, Emrah; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Master Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 26207; 16372
    We propose an adaptive motion-compensated temporal filtering (MCTF) structure to provide efficient temporal scalability within the H.264./AVC video compression standard. MCTF has traditionally been considered within fully scalable wavelet video coders. However, motion-compensated simple 5/3 lifted temporal wavelet filtering suffers at scene changes, as well as Occlusion regions. We note that the bi-directional motion compensation mode in the H.264 standard is best equipped with the state of the art adaptive features Such as adaptive block size, mode switching, between forward, backward and bidirectional prediction and in-loop deblocking filter. Hence, we propose a GOP structure to implement block-based adaptive MCTF within the H.264 syntax using stored B-pictures, similar to the motion-compensated 5/3 wavelet filtering. We provide experimental results to compare the results Of Our proposed codec with those of other scalable wavelet video coders which use MCTF. It is also possible to employ the proposed adaptive MCTF structure within fully scalable wavelet video codecs./ Öz: Bu paligmada etkili zamansal ölçeklenebilirlik sağlanması amacıyla H.264 standardı içerisinde devinim dengeli zamansal filtreleme(DDZF) öneriyoruz. DDZF geleneksel olarak dalgacık dönüşümleriyle yapılan tam ölçeklenebilir video kodlamasında kullanılır. Ancak devinim dengeli 5-3 dalgacıkları kaldırma işlemi yapılarak filtreleme görüntü değişimi olan yerlerde ve video çerçevelerinde yeni çıkan bölgelerin kodlanmasında başarısız olmaktadır. H.264 standardı iki yönlü devinim dengeleme için uyarlanabilir blok büyüklüğü, ileri-geri ve iki yönlü modlar arasında uyarlanabilir mod seçimi, bloksuzlaştırma filtresi ve örtüşmeli devinim dengeleme gibi gelişmiş tekniklere sahiptir. Bu nedenle devinim dengeli 5-3 dalgacık filtresine benzer şekilde H.264 standardı içerisinde blok tabanlı uyarlanabilir DDZF uygulamak için bir görüntü grubu yapısı öneriyoruz. Diğer DDZF tabanlı dalgacık dönüşüm video kodlayıcılarının sonuçlarıyla birlikte karşılaştırmak üzere sonuçlarımızı sunuyoruz... Önerdiğimiz DDZF yapısı diğer dalgacık dönüşümü tabanlı video kodlayıcılarında da uygulanabilir.
  • Placeholder
    PublicationMetadata only
    Multiple description video coding with adaptive number of descriptions
    (Institute of Electrical and Electronics Engineers (IEEE), 2005) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Akyol, Emrah; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Master Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 26207; 16372
    Multiple description video coding methods can mitigate the effects of packet losses introduced by congestion and/or bit errors. However, the proposed multiple description video coders are not adaptive to network conditions. In this paper, we propose a novel multiple description video coding technique, based on the state-of-the art scalable video coding scheme, which provides flexibility in the number of descriptions, redundancy in descriptions and the bitrate of each description by manipulating the encoded bitstream, post encoding. Also, the proposed method provides excellent coding efficiency, outperforming most other multiple description methods proposed so far. We compare the performance of the proposed method to other multiple description video coders. We also show the use of changing the number of descriptions according to network conditions, by an NS-2 network simulation of a peer-to-peer video streaming system. / İletişim kanallardaki sıkışmanın neden olduğu paket kayıpları ve gecikme değişimleri, gecikmeye duyarlı multimedya akışı işlemlerini zorlaştırmaktadır. Çok tanımlı video kodlama yöntemleri ile paket kayıplarının yarattığı bu etki azaltılabilmektedir. Ancak bu zamana kadar geliştirilen çok tanımlı video kodlama teknikleri, kanal koşullarına uyum sağlayamamakta, zaman içerisinde tanım sayısının, tanımların içerisine eklenen gereksiz bit miktarinin ve her tanım için harcanan bit miktarının değiştirilmesine izin vermemektedir. Önerilen çok tanımlı video kodlama tekniği bütün bahsedilen değişikliklere olanak sağlamakta ve birçok çok tanımlı video kodlama tekniğinden daha iyi sıkıştırma performansı sergilemektedir. Bu çalışmada önerilen sıkıştırma tekniği diğer benzer tekniklerle birçok değişken koşulda karşılaştırılmış, önerilen tekniğin diğer tekniklere hem sağladığı çok yönlü kanala uyarlanabilme özelliği açısından hem de sıkıştırma performansı ve video görüntü kalitesi (PSNR) açısından üstün olduğu gösterilmiştir.
  • Placeholder
    PublicationMetadata only
    Optimal bit allocation in scalable multiple description video coding for packet loss resilience
    (Institute of Electrical and Electronics Engineers (IEEE), 2005) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Akyol, Emrah; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Master Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 26207; 16372
    Scalable multiple description video coders (SMDC) allow for better adaptation of video transmission to varying network conditions with compression efficiency comparable to that of non-scalable MDC coders. Recently, we proposed a new SMDC video coding framework, which offers flexibility in the number of descriptions, redundancy level in each description, and bitrate of each description by post encoding processing only [2]. In this work, we propose a low complexity algorithm to find the best low and high rates for this new framework to strike the optimal trade off between compression efficiency and error resilience at a given packet loss rate. We provide experimental results, by means of network simulations, to compare our method with SMDC using a fixed number of descriptions and fixed redundancy level.
  • Placeholder
    PublicationMetadata only
    Motion compensated temporal filtering within the H.264 standard
    (IEEE, 2004) Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; N/A; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Akyol, Emrah; Faculty Member; Faculty Member; Master Student; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; 26207; 16372; N/A
    We propose an adaptive motion-compensated temporal filtering (MCTF) structure to provide efficient temporal scalability within the H.264./AVC video compression standard. MCTF has traditionally been considered within fully scalable wavelet video coders. However, motion-compensated simple 5/3 lifted temporal wavelet filtering suffers at scene changes, as well as occlusion regions. We note that the bi-directional motion compensation mode in the H.264 standard is best equipped with the state of the art adaptive features such as adaptive block size, overlapped block motion compensation, mode switching between forward, backward and bidirectional prediction, and in-loop deblocking filter. Hence, we propose a GOP structure to implement block-based adaptive MCTF within the H.264 syntax using stored B-pictures, similar to the motion-compensated 5/3 wavelet filtering. We provide experimental results to compare the results of our proposed codec with those of other scalable wavelet video coders which use MCTF. It is also possible to employ the proposed adaptive MCTF structure within fully scalable wavelet video codecs.
  • Placeholder
    PublicationMetadata only
    Content- adaptive scaling option selection in scalable video coding
    (Institute of Electrical and Electronics Engineers (IEEE), 2005) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Akyol, Emrah; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Master Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 26207; 16372
    Scalable video coders provide different options, such as temporal, spatial and SNR scalability, each option results in different kinds and levels of visual distortion depending on the content. We observe that a single scalability option does not fit the whole video content well, and the scalability operator should be varied for different temporal segments depending on the content of the segment. We propose a method to choose the best scaling option that results in minimum visual distortion. We employ four component metrics to quantify artifacts caused by bitrate reduction, spatial size reduction and temporal subsampling, which are a flatness measure, a blockiness measure, a blurriness measure, and a jerkiness measure. We define the best scaling operator as the one with the minimum distortion score which is given by a linear combination of these four component measures. Two subjective tests have been performed to validate the proposed procedure for optimal selection of scalability operators for soccer videos. / Ölçeklenebilir video kodlayıcıları, her biri içeriğe ve bithızına bağlı olarak değişik tipte ve miktarda bozuluma neden olan zamansal, uzaysal ve kalitesel olmak üzere üç çeşit ölçeklenebilirlik olanağı sağlamaktadır. Genelde bir tek ölçekleme operatörü videonun bütün kısımları için uygun olmamaktadır; bu nedenle videonun değişik içerikteki her bir parçası için ölçekleme operatörü o parçanın içeriğine bağlı olacak şekilde değiştirilmelidir. Bu çalışmada, video bir içerik inceleme metoduyla içeriğine bağlı olarak değişik kısımlara ayrılmış kabul edilmiş ve her bir zamansal video parçası (shot) en düşük bozunuma sonuç veren en-iyi ölçekleme operatörüyle ölçeklenmiştir. Bit-hızı azalımı, uzaysal genişlik değişimi ve zamansal ölçeklemenin yarattığı bozulum, düzlük, blokluluk, zamansal atlama ve bozunukluk metrikleriyle ölçülmüştür. Eniyi ölçekleme operatörü ayrı bozulum metriklerinin lineer kombinasyonuyla oluşturulan genel bozulum metrigine gore en düşük bozulumu veren operator olarak bulunmuştur. Bu lineer kombinasyonun katsayıları içeriğe göre ayarlanarak bulunmuştur. Önerilen bozulum metriği ve en-iyi operatör bulma prosedürü futbol videolarıyla iki öznel test yapılarak gerçeklenmiştir.
  • Placeholder
    PublicationMetadata only
    Optimum scaling operator selection in scalable video coding
    (IEEE, 2004) Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; N/A; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Akyol, Emrah; Faculty Member; Faculty Member; Master Student; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; 26207; 16372; N/A
    Scalable video coders provide different options, such as temporal, spatial and SNR scalability, where each option results in different kinds and/or levels of visual distortion at the lower scales depending on the content and bitrate. We observe that in most cases a single scalability option does not fit the whole video content well, and the scalability operator should be varied for different temporal segments depending on the content of the segment. In this work, assuming the video is temporally segmented by some content analysis scheme, we propose a method to choose the visually best scaling option that results in minimum visual distortion among temporal, spatial and SNR scalability operators for each temporal segment of soccer videos. We employ four component metrics to quantify artifacts caused by bitrate reduction, spatial size reduction and temporal subsampling, which are a flatness measure, a blockiness measure, a blurriness measure, and a temporal distortion (jerkiness) measure. We then define the best scaling operator for each video segment as the one with the minimum distortion score which is given by a linear combination of these four component measures. Coefficients of this linear combination are tuned to content type using a training procedure. Two subjective tests have been performed to validate the proposed distortion measures and procedure for optimal selection of scalability operators for soccer videos.