Pose Information Generation Using Fixed Spatial Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately generate pose information for a person in a physical environment, which is crucial for providing realistic computer-generated reality (CGR) experiences.
Innovation Solution
A device comprising environmental sensors, processors, and memory, which captures spatial data of a physical environment, identifies body portions, determines their positions relative to fixed spatial points, and generates pose information for the person.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If environmental sensors and spatial data processing are used to generate pose information, then measurement precision of body position is improved, but device complexity increases
Solution Approach 1:
The system segments the complex task of pose estimation into distinct functional modules: environmental sensors capture spatial data, processors identify body portions, determine positions relative to fixed points, and generate pose information. This modular segmentation allows each component to specialize in a specific subtask, improving overall measurement precision while making the complex system more manageable and maintainable
Solution Approach 2:
The system introduces fixed spatial points as intermediary reference markers in the physical environment. These intermediaries serve as mediators between the sensors and the body portions being tracked, providing stable reference frames that enhance measurement precision without requiring direct complex interactions between sensors and all body parts simultaneously
2Loss of information
If multiple body portions are tracked to enhance CGR realism, then information completeness is improved, but processing time increases
Solution Approach 1:
The system performs preliminary identification and classification of body portions before full pose calculation. By pre-identifying which body portions are visible and relevant in the current view, the system prepares data structures and reference frames in advance, allowing faster processing when complete pose information is needed for CGR rendering
Solution Approach 2:
The system tracks multiple body portions beyond what might be strictly necessary for basic pose estimation. By capturing excessive pose data from more body parts than minimally required, the system ensures information completeness for realistic CGR avatars while the processing pipeline is optimized to handle this extended data set efficiently
Data Source
AI summary
In various implementations, a device includes an environmental sensor, a non-transitory memory and one or more processors coupled with the environmental sensor and the non-transitory memory. In some implementations, a method includes, while the device is in a physical environment that includes a fixed spatial point and a person, obtaining, via the environmental sensor, spatial data corresponding to a-physical environment and the person. The method includes determining, based on the spatial data, a position of a first body portion of the person relative to the fixed spatial point. Determining the position of the first body portion is based on a distance between the device and the fixed spatial point and based on a distance between the device and the first body portion. The method includes generating, based on the position of the first body portion, pose information for the first body portion relative to the fixed spatial point.