Wrist-Worn Sensor 3D Hand Tracking via Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable sensors for tracking articulated body parts are cumbersome, restrictive, and limited in their ability to accurately detect fine gestures due to size, weight, and power consumption constraints, often requiring users to wear gloves or markers.
Innovation Solution
A wrist-worn device with a camera and structured illumination source that captures images of the hand to track 3D poses without the need for gloves or markers, using an inertial measurement unit to enable tracking of the arm and hand, allowing for gesture-based control of computing devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Weight of moving object
If wearable sensors are made smaller and lighter to reduce burden on wearer, then comfort and ease of wear is improved, but tracking accuracy and fidelity of articulated body parts decreases
Solution Approach 1:
The system segments the tracking functionality across multiple components: a wrist-worn sensor unit for capturing images and basic data, and a separate computing device for performing complex articulated model tracking and gesture recognition. This division allows the wearable portion to remain lightweight while the processing burden is shifted to the external computing device.
Solution Approach 2:
The patent introduces an intermediary computing device that receives data from the lightweight wrist-worn sensor and performs the computationally intensive tasks of 3D reconstruction and articulated model tracking. This intermediary handles the heavy processing requirements, enabling the wearable sensor itself to remain small and comfortable.
2Measurement precision
If more sensors and processing components are added to improve tracking fidelity, then measurement precision is improved, but device complexity and power consumption increase
Solution Approach 1:
The patent extracts the complex processing functions (articulated model tracking, 3D reconstruction, gesture recognition) from the wearable sensor and places them in an external computing device. The wrist-worn unit retains only the essential sensing and image capture functions, dramatically reducing its complexity while maintaining high tracking fidelity through the external processing system.
Solution Approach 2:
The computing device serves multiple functions: it performs articulated model tracking, gesture recognition, 3D scene reconstruction, and object recognition. This multi-functionality consolidates what would otherwise require multiple separate systems into a single device, reducing overall system complexity while maintaining comprehensive tracking capabilities.
3Measurement precision
If more sensors and processing components are added to improve tracking fidelity, then measurement precision is improved, but power consumption increases
Solution Approach 1:
The patent extracts the power-intensive processing operations from the wearable sensor and relocates them to an external computing device that has its own power source. The wrist-worn sensor only performs low-power image capture and data transmission, dramatically reducing its power consumption while the external device handles all computationally intensive tracking and recognition tasks.
Solution Approach 2:
The system uses periodic action by capturing images at specific intervals and transmitting only necessary data to the computing device. The wrist-worn sensor captures images periodically rather than continuously processing video streams, reducing power consumption while maintaining adequate tracking fidelity through selective image capture and transmission.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate and robust 3D tracking of hand gestures with low computational overhead, allowing for freehand interactions and spatial navigation without interfering with everyday activities, and can be used for object recognition and scene reconstruction.
Implementation Method 1
a camera captures images of an articulated part of a body of a wearer
Implementation Method 2
the device has a structured illumination source and a diffuse illumination source for illuminating the articulated body part
Implementation Method 3
an inertial measurement unit is also included in the sensor to enable tracking of the arm and hand
Data Source
AI summary
A wearable sensor for tracking articulated body parts is described such as a wrist-worn device which enables 3D tracking of fingers and optionally also the arm and hand without the need to wear a glove or markers on the hand. In an embodiment a camera captures images of an articulated part of a body of a wearer of the device and an articulated model of the body part is tracked in real time to enable gesture-based control of a separate computing device such as a smart phone, laptop computer or other computing device. In examples the device has a structured illumination source and a diffuse illumination source for illuminating the articulated body part. In some examples an inertial measurement unit is also included in the sensor to enable tracking of the arm and hand