AR Character Object Action Control via Feature Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality technologies lack the capability to process operations of character objects in a way that is high in zest, meaning they fail to provide engaging and interactive experiences.
Innovation Solution
A non-transitory storage medium encoded with a computer-readable information processing program that includes an image pick-up unit, allowing for the arrangement of objects and character objects in a virtual space, determination of action mastery, storage of character objects and actions, and generation of augmented reality images by superimposing virtual and real space images, with recognition of features in the real space image and controlled performance of actions by character objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional augmented reality methods are used to display virtual character objects, then basic AR functionality is achieved, but the processing of character object operations lacks zest and user engagement
Solution Approach 1:
The system performs preliminary actions by having the character object practice actions in advance and storing mastery information. Before the character object performs an action in the augmented reality scene, the system determines whether the action has been mastered through prior practice sessions. This preliminary preparation enables the character object to perform actions with higher quality and variety without requiring complex real-time decision-making systems.
Solution Approach 2:
The system changes parameters by storing and retrieving mastery information that tracks which actions the character object has mastered. This parameter-based approach allows the system to dynamically adjust character object behavior based on stored mastery levels, enabling versatile operations without increasing structural complexity. The mastery information serves as a parameter that controls action selection and performance quality.
2Adaptability or versatility
If the character object performs multiple actions with high versatility, then user engagement increases, but the system complexity increases
Solution Approach 1:
The system uses copying by storing mastery information that represents learned actions. Instead of implementing complex neural networks or decision-making algorithms, the system copies successful action patterns from practice sessions and stores them as mastery data. This allows the character object to perform multiple actions with high versatility while keeping the control system relatively simple, as the complexity is shifted to data storage rather than real-time processing.
3Reliability
If the character object learns and masters actions through practice, then operation quality improves, but processing time increases
Solution Approach 1:
The system performs preliminary action by conducting practice sessions before the character object needs to perform actions in the augmented reality scene. During these practice sessions, the character object learns and masters actions, and the system stores this mastery information. This preliminary learning phase separates the time-consuming training process from the actual action execution, allowing high-quality action performance without time loss during critical moments.
Solution Approach 2:
The system maintains continuity of useful action by seamlessly transitioning from practice sessions to action execution. The mastery information stored during practice continues to guide character object behavior in subsequent scenes, ensuring that the learning process continuously improves action quality without interrupting the main application flow. The useful action of learning persists across different sessions and scenes.
Data Source
AI summary
A non-transitory storage medium encoded with a computer readable information processing program executed in a computer of an information processing apparatus including an image pick-up unit that picks up an image of a real space is provided. At least one computer is configured to perform operations including generating an augmented reality image by superimposing a virtual space image corresponding to a virtual space that has been picked up by a virtual camera arranged in the virtual space and a real space image corresponding to the real space that has been picked up by the image pick-up unit on each other, recognizing a feature included in the real space image, and controlling, when the real space image includes a feature as a result of recognition, a character object to perform an action at a position associated with the feature included in the real space image.