Loading...

Analysis and Development of Quality Assessment Methods of 360 Videos

Dehqanpour, Mohammad Saleh | 2021

482 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53779 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Sharifkhani, Mohammad
  7. Abstract:
  8. Virtual Reality technologies and its related standards and tools, will play a remarkable role in our future digital life. Development of that topic will be definitely dependent on availability of a reliable, precise and low-cost video quality assessment method. In recent years, there was a significant amount of research works on 360 videos, notably among them are new video quality metrics. Unfortunately in terms of correlation to subjective scores, they are still far from ideal especially with respect to previous performances in regular video domain. In this research we focused on desiging a full-reference 360-video quality assessment method. First, we extracted 2D viewport videos from the whole panorama using the subjects’ watching trajectories. With this technique the video is reduced to a regular traditional video. Then we combined several video quality metrics for traditional videos using a machine learning method to form a new composite quality metric. We used one of existing datasets and so video distortions were confined to what present there which in this case was increasing encding quanization parameter. The dataset contains a total of 48 videos with 12 reference videos and 3 distorted ones for each of them. Our metric has achived a linear correlation of %87 on the testing dataset which is better up to %7 from previous work on that dataset
  9. Keywords:
  10. Video Coding ; 360 Degree Video ; Virtual Reality (VR)Environment ; Video Quality ; Quality Rate Measurement ; Full-Reference Metric ; Video Quality Assessment

 Digital Object List

 Bookmark

No TOC