Skeletal Model Motion Recognition via Body-Based Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing natural user interface (NUI) systems face challenges in accurately recognizing human body motions in real-time, particularly when users perform gestures while moving within the camera's field of view, due to the need to decouple arm actions from overall motion and account for varying speeds, which complicates gesture determination and responsive actions.
Innovation Solution
The technology employs a skeletal model representing the human body as joints and bones, using a camera-based 3-D coordinate system that is transformed into a body-based system, allowing for temporal scaling and efficient determination of motion, enabling real-time gesture recognition independent of camera view and user speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If camera-based 3-D coordinate system is used to track user motion, then real-time motion detection is achieved, but complexity increases when decoupling body part motions from overall movement
Solution Approach 1:
The system segments the coordinate reference system into camera-based and body-based systems. By transforming skeletal data from the camera-based system to a body-based system that moves with the user, the system separates overall body movement from individual body part motions, enabling real-time processing without complex decoupling calculations.
Solution Approach 2:
The body-based coordinate system acts as an intermediary between the camera-based system and the gesture recognition logic. This intermediate reference frame simplifies the analysis of body part motions by providing a stable frame that moves with the user, eliminating the need for complex real-time decoupling calculations.
2Adaptability or versatility
If user moves around in camera field of view while performing gestures, then natural interaction is enabled, but accuracy of gesture recognition decreases due to motion trajectory complexity
Solution Approach 1:
Instead of analyzing body part motions relative to the stationary camera-based coordinate system, the system inverts the approach by transforming all skeletal data into a body-based coordinate system that moves with the user. This inversion makes the user the reference point, simplifying gesture analysis regardless of the user's position or movement in the camera field of view.
3Adaptability or versatility
If gesture recognition must account for varying user speeds, then comprehensive motion analysis is achieved, but processing time increases beyond frame rate requirements
Solution Approach 1:
The system performs preliminary transformation of skeletal data from the camera-based coordinate system to the body-based coordinate system for each frame. This preliminary action establishes a consistent reference frame that automatically accounts for varying user speeds, eliminating the need for additional complex calculations that would exceed frame rate requirements.
Data Source
AI summary
Human body motion is represented by a skeletal model derived from image data of a user. The model represents joints and bones and has a rigid body portion. The sets of body data are scaled to a predetermined number of sets for a number of periodic units. A body-based coordinate 3-D reference system having a frame of reference defined with respect to a position within the rigid body portion of the skeletal model is generated. The body-based coordinate 3-D reference system is independent of the camera's field of view. The scaled data and representation of relative motion within an orthogonal body-based 3-D reference system decreases the data and simplifies the calculations for determining motion thus enhancing real-time performance for multimedia applications controlled by a user's natural movements.