Blind Area Position Tracking for XR Handles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Extended reality devices face challenges in accurately determining the position of handles within blind areas of cameras, leading to inaccurate position prediction and resource wastage due to continuous neural network operation.
Innovation Solution
A position determining method that uses a historical time queue to store position information of a target object at previous moments, determining whether the target object is outside the blind area of the camera at both historical and current moments, and only using optical tracking when the target object is outside the blind area, thereby avoiding resource wastage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the neural network operates continuously to predict handle position, then position prediction capability is maintained, but resource consumption increases
Solution Approach 1:
The system dynamically adjusts the operational state of the position estimation model based on real-time conditions. When the handle is detected to be in the blind area of the camera, the neural network is activated to perform position prediction. When the handle is outside the blind area, the system uses direct optical tracking without activating the neural network, thereby reducing resource consumption while maintaining prediction reliability when needed.
Solution Approach 2:
The system periodically checks whether the handle is located in the blind area and activates or deactivates the position estimation model accordingly. This periodic activation based on spatial conditions allows the system to maintain accurate position prediction when required while avoiding continuous operation that would waste computational resources.
2Measurement precision
If the position estimation model operates continuously, then position determination accuracy is maintained, but computational resources are wasted
Solution Approach 1:
The system dynamically switches between two operational modes: neural network-based prediction when the handle is in the blind area, and direct optical tracking when the handle is outside the blind area. This dynamic switching ensures that computational resources are allocated only when necessary for accurate position determination, improving overall computational efficiency without sacrificing measurement precision.
Solution Approach 2:
The system uses its own detection capabilities (camera-based blind area detection) to automatically determine when the position estimation model should be activated or deactivated. This self-service mechanism eliminates the need for external control and optimizes resource usage based on real-time spatial conditions.
Data Source
AI summary
The present disclosure provides a position determining method and apparatus, an electronic device and a storage medium. The method includes: determining whether a target object is located in a blind area of a camera at n historical moments of a historical time queue and a target moment; wherein the historical time queue is configured to store historical position information of the target object at latest n historical moments prior to the target moment, where n is a preset positive integer not less than 2; and in response to the target object being located outside the blind area of the camera at both of the n historical moments and the target moment, determining position information of the target object acquired by the camera at the target moment as the position information of the target object at the target moment.