360-Degree Video Region Evaluation via Emotion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing systems fail to accurately identify and update the region of interest in virtual spaces based on user emotions and actions, leading to missed exciting content points during 360-degree moving image playback.
Innovation Solution
An information processing method that defines a virtual space, detects head-mounted device motion, generates a visual-field image, identifies user emotions, and updates evaluation values of regions based on user actions and emotions, ensuring that exciting content points are not missed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system monitors user emotions and actions to identify regions of interest, then the accuracy of region identification is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system segments the 360-degree moving image into multiple regions and processes each region independently. The evaluation value calculation is performed on a per-region basis, allowing parallel processing and reducing overall computational complexity while maintaining high identification accuracy through localized analysis.
Solution Approach 2:
The system pre-calculates evaluation values for multiple regions simultaneously based on user emotions and actions detected during playback. By performing these calculations in advance and storing them, the system reduces real-time processing burden while ensuring accurate region identification when needed.
2Speed
If the system updates evaluation values in real-time based on user emotions, then the responsiveness is improved, but the energy consumption increases
Solution Approach 1:
The system updates evaluation values at specific periodic intervals rather than continuously. It identifies key moments during playback where user emotions change significantly and updates region evaluation values at these discrete points, reducing energy consumption while maintaining responsive performance.
Solution Approach 2:
The system automatically detects changes in user emotions and actions, and autonomously determines when and which regions need evaluation value updates. This self-service mechanism avoids unnecessary continuous processing, reducing energy consumption while maintaining real-time responsiveness to genuine user engagement changes.
3Adaptability or versatility
If the system processes multiple user inputs simultaneously, then the user experience quality is improved, but the measurement precision of individual emotions decreases
Solution Approach 1:
The system segments user data by assigning unique identifiers to each user and processing their emotions and actions separately. Each user's region evaluation values are calculated independently based on their individual emotions and actions, ensuring high measurement precision for each user while supporting multiple users simultaneously through this segmented processing approach.
Data Source
AI summary
A method includes defining a virtual space including a 360-degree moving image. The method includes playing back the 360-degree moving image. The method includes detecting a motion of a head-mounted device (HMD). The method includes defining a visual field in the 360-degree moving image based on the detected motion. The method includes detecting an emotion of a first user. The method includes comparing the detected emotion with a first condition. The method includes identifying a playback time of the 360-degree moving image at a timing of satisfaction of the first condition. The method includes identifying a direction indicated by the first user at the timing of satisfaction of the first condition. The method includes identifying a first region including a part of the 360-degree moving image corresponding to the identified direction. The method includes changing an evaluation value of the first region in response to satisfaction of the first condition.