Geri Dön

Quality estimation and delivery of visual contents with different spatial resolutions

.

PDF İndir

  1. Tez No: 598202
  2. Yazar: ALİ MURAT DEMİRTAŞ
  3. Danışmanlar: PROF. HAMİD JAFARKHANİ
  4. Tez Türü: Doktora
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Elektrik ve Elektronik Mühendisliği, Computer Engineering and Computer Science and Control, Electrical and Electronics Engineering
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2015
  8. Dil: İngilizce
  9. Üniversite: University of California Irvine
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Belirtilmemiş.
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: 93

Özet

.

Özet (Çeviri)

In this thesis, we work on quality estimation and delivery of visual content with di erent spatial resolutions. First, we study the quality estimation of images with di erent spatial resolutions. Estimating the quality of the visual content accurately is crucial in providing sat- isfactory multimedia communication. State of the art visual quality assessment approaches are e ective when the input image and the reference image have the same resolution. How- ever, nding the quality of an image that has spatial resolution di erent than that of the reference image is still a challenging problem. To solve this problem, we develop a qual- ity estimator (QE) which computes the quality of the input image without resampling the reference or the input images. We begin by identifying the potential weaknesses of previ- ous approaches used to estimate the quality of experience. Next, we design a QE, called Multiscale Image Quality Estimator (MIQE), to estimate the quality of a distorted image with a lower resolution compared to the reference image. We also propose a subjective test environment to explore the success of the proposed algorithm in comparison with other QEs. When the input and test images have di erent resolutions, the subjective tests demonstrate that in most cases the proposed method works better than other approaches. In addition, the proposed algorithm also performs well when the reference image and the test image have the same resolution. Second, we examine the quality estimation of videos with di erent spatial resolutions. Full- reference video QEs either resize the distorted input video or the reference video to compute the quality when these videos have di erent spatial resolutions. This resizing operation causes several limitations. MIQE overcomes those limitations for images but it does not consider the temporal characteristics of video. We develop a full-reference video quality estimator that integrates MIQE with the motion information to estimate the quality of the distorted video without resampling the reference or the test videos. We also perform subjective tests to compare the proposed algorithm with the existing QEs. In these tests, the reference and the input videos are displayed at their native resolutions. Test results show that the proposed algorithm outperforms other QEs when the reference video and the input video have di erent spatial resolutions. We have also evaluated the performance of the approach using the Scalable Video Database. Third, we work on the challenge of using a perceptual quality estimator to perform optimum multicasting of videos to the devices with di erent spatial resolutions. We speci cally focus on the complexity of the optimum perceptual multicasting. The complexity increases due to usage of scalable video coding in combined scalability mode and perceptual quality esti- mators. Using combined scalability increases the number of scalability options, so we need to perform multi-criteria optimization. As a result of the simulations we have performed, we have observed that multi-criteria optimization is not necessary in the low bitrate region, and we propose an algorithm to reduce the complexity of the optimization notably for this region.

Benzer Tezler

  1. Tez No

    292361

    Kamu inşaat sektöründe yaklaşık maliyet hesabı şartnamesi oluşturulmasına yönelik bir çalışma

    A sample study for constituting a detailed cost estimate specification in public construction sector

    DUYGU TOKALAKOĞLU

    Yüksek Lisans

    Türkçe

    Türkçe

    2010

    Mimarlıkİstanbul Teknik Üniversitesi

    Mimarlık Ana Bilim Dalı

    DOÇ. DR. ELÇİN TAŞ

  2. Tez No

    676778

    Kauçuk katkılı modifiye bitüm kullanılarak mastik asfalt uygulanması

    Using rubber additive modified bitumen mastic asphalt application

    SALİH ALUÇ

    Yüksek Lisans

    Türkçe

    Türkçe

    2021

    UlaşımKastamonu Üniversitesi

    Malzeme Bilimi ve Mühendisliği Ana Bilim Dalı

    DR. ADEM AHISKALI

  3. Tez No

    71798

    Hizmet sektöründe toplam kalite yönetimi

    Başlık çevirisi yok

    HÜNKAR ŞERİF

    Yüksek Lisans

    Türkçe

    Türkçe

    1998

    İşletmeMarmara Üniversitesi

    Bankacılık Ana Bilim Dalı

    PROF. DR. İ. METE DOĞRUER

  4. Tez No

    712817

    Order dispatching via deep reinforcement learning

    Başlık çevirisi yok

    ERAY MERT KAVUK

    Yüksek Lisans

    İngilizce

    İngilizce

    2022

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    DR. ÖĞR. ÜYESİ AYŞE TOSUN KÜHN

  5. Tez No

    84241

    Yazılım geliştirme metrikleri ve yazılımD proje izleme sistemi geliştirimi

    Software development metrics and implementation of yazılımD project tracking system

    MUSTAFA SENCER SULTANOĞLU

    Yüksek Lisans

    Türkçe

    Türkçe

    1999

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolHacettepe Üniversitesi

    Bilgisayar Bilimleri Ana Bilim Dalı

    PROF. DR. ÜMİT KARAKAŞ

Geri Dön