Fixed-Camera AR Pose Estimation Without 6DoF Translation Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) systems require complex configurations to estimate the position and attitude of a camera, especially when the camera is fixed, as in sports events, necessitating detection of 6 degrees of freedom (6DoF) which is not necessary for fixed cameras.
Innovation Solution
An information processing apparatus and system that determines translational movements (forward/backward, left/right, up/down) of a fixed camera using sensing data, allowing for the detection of only 3 degrees of freedom (3DoF) rotations, thereby simplifying the system configuration and improving AR video generation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If 6DoF estimation is used for camera position and attitude in AR systems, then the accuracy of virtual video combination is improved, but the system configuration becomes complex and additional equipment is required
Solution Approach 1:
The patent extracts and removes the translation detection function from the AR system, recognizing that fixed cameras do not require translation detection. By eliminating this unnecessary function, the system achieves 3DoF estimation instead of 6DoF, reducing device complexity while maintaining sufficient accuracy for virtual video combination
Solution Approach 2:
The patent changes the parameter of degree of freedom estimation from 6DoF to 3DoF based on the fixed camera condition. This parameter change reduces the computational load and equipment requirements while maintaining adequate precision for the specific application scenario of fixed camera AR imaging
2Reliability
If translation detection is performed for fixed cameras, then erroneous translational movements can be detected, but the system complexity increases unnecessarily
Solution Approach 1:
The patent removes the translation detection component from the system, recognizing that fixed cameras inherently prevent translation. The system relies on the physical constraint of the fixed mounting rather than active detection, thereby reducing device complexity while maintaining reliability through the mechanical stability of the fixed position
Data Source
AI summary
An information processing apparatus includes a translation determination unit that determines whether or not there is a translational movement forward/backward, left/right, or up/down from a fixed position on the basis of sensing data indicating a state of a camera that captures a live-action video to be used for combination with a virtual video and whose image capturing position is fixed.