Sensor-Assisted Wearable Device Tracking Beyond Imaging View
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing device position estimation technologies fail when the device moves out of the imaging apparatus' view, leading to discontinuous acquisition of position information.
Innovation Solution
An information processing apparatus that acquires position and posture information from a first device worn on a user, and uses sensor data to adjust the degree of following a skeleton model to estimate the position of a second device based on the first device, allowing continuous tracking regardless of the device's position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If device position estimation is based on marker images captured by an imaging apparatus, then position information can be acquired when the device is within the viewing range, but position information cannot be acquired when the device moves out of the viewing range
Solution Approach 1:
The patent combines image-based position estimation (using marker images from imaging apparatus) and sensor-based position estimation (using sensors on the device) into a unified system. When the device is within the imaging range, image-based estimation is used for high precision. When the device moves out of range, the system seamlessly transitions to sensor-based estimation using data from accelerometers, gyroscopes, and other sensors, ensuring continuous tracking without interruption.
Solution Approach 2:
The patent introduces a switching mechanism that acts as an intermediary between image-based and sensor-based estimation methods. This mediator determines which method to use based on whether marker images are detectable, and smoothly transitions between methods to maintain continuous position information acquisition regardless of device location.
2Measurement precision
If only image-based position estimation is used, then high measurement precision can be achieved when markers are visible, but the system cannot function when markers are out of view
Solution Approach 1:
The patent changes the estimation method parameter based on the visibility condition of marker images. When markers are visible, the system uses image processing parameters for high-precision estimation. When markers become invisible, the system switches to sensor fusion parameters, combining data from accelerometers, gyroscopes, and other sensors to maintain reliable position estimation without interruption.
3Adaptability or versatility
If the system switches between image-based and sensor-based estimation, then continuous position acquisition is enabled, but system complexity increases
Solution Approach 1:
The patent implements a dynamic switching mechanism that adapts the estimation method based on real-time conditions. The system continuously monitors whether marker images are detectable and dynamically switches between image-based and sensor-based estimation methods. This dynamic approach enables comprehensive tracking coverage while managing system complexity through condition-based method selection rather than maintaining both systems simultaneously.
Data Source
AI summary
Disclosed herein is an information processing apparatus including a first device information acquisition section that acquires position and posture information relating to a first device worn on a user, a second device information acquisition section that acquires position information relating to a second device worn on a portion different from the first device on the basis of the position and posture information relating to the first device and a skeleton model of a human, and a sensor data acquisition section that acquires sensor data from a sensor that measures motions of the first device and the second device. The second device information acquisition section changes a degree of following of the skeleton model to the first device on a basis of the sensor data.