Twin Pose Detection via Interactive Indirect Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current virtual reality technologies face limitations in pose detection due to the need for specialized sensors and peripherals, which restrict accessibility and consistency, making it difficult for universal users to engage with virtual reality applications anywhere and anytime.
Innovation Solution
A twin pose detection method based on interactive indirect inference using mobile smart devices, which acquires data through intrinsic sensors like gyroscopes, acceleration, and touch sensors to reason and generate virtual poses without the need for external assistive devices, relying on human mechanics constraints to ensure accurate and dynamic pose detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If specialized sensors and assistive peripherals (such as HMDs, handles, wearable pose positioners) are used for pose detection, then measurement precision and reliability of pose detection are improved, but device complexity and cost increase, and accessibility and universality deteriorate
Solution Approach 1:
The patent extracts the pose detection functionality from specialized external sensors and peripherals, and relocates it to the mobile terminal itself using its intrinsic sensors (accelerometer, gyroscope, magnetometer, touch screen, camera). This extraction eliminates the need for additional assistive devices while maintaining pose detection capability.
Solution Approach 2:
The mobile terminal performs pose detection for itself and the user using its own built-in sensors without requiring external assistive devices. The terminal's intrinsic sensors (accelerometer, gyroscope, magnetometer, touch screen, camera) are utilized to detect the terminal's pose and infer the user's pose, making the system self-sufficient.
2Measurement precision
If specialized sensors and assistive peripherals are used for pose detection, then measurement precision is improved, but ease of operation and accessibility worsen due to wearability and compatibility limitations
Solution Approach 1:
The patent makes the mobile terminal universal by enabling it to perform pose detection without requiring specialized peripherals. The terminal uses its existing multi-functional sensors (accelerometer, gyroscope, magnetometer, touch screen, camera) to detect both terminal pose and user pose, making the system accessible to all mobile phone users regardless of whether they wear HMDs or use other assistive devices.
Solution Approach 2:
Instead of using external sensors to directly measure user pose, the patent inverts the approach by measuring terminal pose using intrinsic sensors and then inferring user pose through interaction models. This inversion allows the system to work with any mobile terminal regardless of the user's equipment.
3Measurement precision
If additional camera image capture equipment is used for pose detection, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the imaging function from separate camera equipment and integrates it into the mobile terminal using its built-in camera. The terminal's camera works in conjunction with intrinsic sensors to capture images and detect poses, eliminating the need for additional camera devices.
Solution Approach 2:
The patent merges multiple sensing functions (accelerometer, gyroscope, magnetometer, touch screen, camera) into a unified pose detection system within the mobile terminal. These sensors work together to detect terminal pose and infer user pose, combining multiple capabilities into a single integrated system.
Data Source
AI summary
A method and system for twin pose detection based on interactive indirect inference. The method includes: acquiring, by sensors on a mobile phone, a data set in real time; and obtaining poses of individual parts of a skeleton of an object by reasoning using reasoners on individual parts based on the data set and a preferred way of the object for using the mobile phone; merging the poses to generate multiple initial virtual skeletons; under a predetermined human mechanics constraint, obtaining multiple overall virtual skeletons satisfying the predetermined human mechanics constraint from the initial virtual skeletons; and screening a predetermined number of overall virtual skeletons from the overall virtual skeletons, and obtaining a dynamic twin virtual pose in real time by reasoning on the predetermined number of overall virtual skeletons using an overall skeleton reasoner.