Stabilizing AR Material Presentation via Multi-Frame Key Point Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the context of short video recording and photographing, the shaking of camera or shooting objects during video recording leads to significant shaking of key points, resulting in large amplitude material shaking and poor fitting with the object, making it difficult to present materials effectively.
Innovation Solution
A method and apparatus that acquire multiple key points from an object in a current image, determine a preselected target point based on these key points, and then determine a target point for the current image by analyzing continuous frames of images, allowing for stable presentation of materials by averaging or using geometric centers and shapes formed by key points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If key points are used for material presentation, then material alignment with objects is achieved, but camera or object shaking causes significant key point displacement and large amplitude material shaking
Solution Approach 1:
The patent performs preliminary actions by acquiring multiple key points from continuous N frames of images before determining the final target point. This preliminary acquisition of key point data from multiple frames allows the system to pre-process and stabilize the position information, reducing the impact of shaking when presenting materials.
Solution Approach 2:
The patent introduces an intermediary computational process that determines a target point based on multiple key points from continuous frames rather than directly using single-frame key points. This intermediary step acts as a mediator that filters out shaking effects by analyzing key point positions across multiple frames, thereby stabilizing the material presentation while maintaining alignment accuracy.
2Productivity
If single frame key points are used for material presentation, then processing speed is fast, but shaking causes poor fitting and ineffective material presentation
Solution Approach 1:
The patent applies partial action by using a limited number of continuous frames (N frames) rather than processing entire video sequences. This partial processing approach maintains relatively fast processing speed while sufficiently reducing shaking effects. The system processes only the necessary portion of frame data required to achieve stable material presentation without excessive computational overhead.
Data Source
AI summary
Disclosed are a method and apparatus for presenting material, and a storage medium. The method includes acquiring at least two key points from a position of a presentation part of an object in an image; determining a preselected target point based on positions of the at least two key points; determining a target point of the image based on the preselected target point and target points of N continuous frames before the image, and presenting the material based on the target point.