QoE evaluation based on user values and context and its application for free viewpoint video

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K12060
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61020:Human interface and interaction-related
• Research Institution: Yamanashi Eiwa College
• Principal Investigator: Inazumi Yasuhiro 山梨英和大学, 人間文化学部, 准教授 (30367255)
• Co-Investigator(Kenkyū-buntansha): 松田 崇弘 東京都立大学, システムデザイン研究科, 教授 (50314381)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: QoE / ユーザの価値観 / コンテキスト / 自由視点映像

Outline of Final Research Achievements

The purpose of this study is to estimate the user-friendly QoE for free viewpoint video application technology. Therefore, in this study, we consider semantic information that is connected among images from different viewpoints. To develop a QoE evaluation method based on semantic information by representing the three-dimensional space of free viewpoint video as semantic information, we implemented an algorithm for extracting semantic information using deep learning on still images. This enabled us to construct an objective QoE evaluation model for still images.

Free Research Field

情報通信工学

Academic Significance and Societal Importance of the Research Achievements

本研究では、「画素集合の比較」ではなく「意味情報の比較」によるQoE評価モデルを実装することが可能となった。この知見は、自由視点映像だけではなく、あらゆる映像信号処理の問題を「意味情報の比較」に捉え直す可能性があり、応用範囲が広いと考えられる。