Posture Detection Using 2D Camera and ToF Depth Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current solutions for detecting human posture in user computing devices are either too expensive, resource-intensive, or inaccurate due to reliance on proprietary sensors and complex machine learning models, making them impractical for consumer-level devices that require cost-effective and accurate ergonomic feedback to improve user health.
Innovation Solution
A contactless posture detection system using a combination of a 2D camera sensor and a low-resolution time-of-flight (ToF) depth sensor, which provides depth information to enhance the accuracy of posture determination through a fusion model, allowing for dynamic and accurate ergonomic feedback without straining the device's resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If proprietary sensors and complex machine learning models are used for posture detection, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent combines a 2D camera sensor and a time-of-flight depth sensor into a unified posture detection system. The 2D camera captures color images while the depth sensor provides distance information, and their data are fused through machine learning models to achieve accurate posture detection without requiring proprietary high-cost sensors
Solution Approach 2:
The patent introduces machine learning models as intermediaries that process and interpret raw sensor data from the 2D camera and depth sensor. These models transform the sensor inputs into meaningful posture information, enabling accurate detection while using inexpensive, commercially available sensors rather than proprietary ones
2Measurement precision
If high-resolution depth sensors are used, then measurement precision is improved, but use of energy and computational resources increase
Solution Approach 1:
The patent uses a low-resolution depth sensor instead of high-resolution depth sensors, accepting lower depth measurement precision in exchange for significantly reduced computational resource consumption and energy usage. The system compensates for the lower resolution by fusing depth data with 2D camera imagery through machine learning models
Solution Approach 2:
The patent changes the resolution parameter of the depth sensor from high to low, fundamentally altering the system's resource profile. This parameter change reduces the computational burden and energy consumption while maintaining acceptable posture detection accuracy through data fusion with the 2D camera
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
The system effectively improves posture detection accuracy while being cost-effective and resource-efficient, enabling widespread adoption in consumer devices to promote better ergonomics and user health by providing real-time feedback on correct or incorrect posture.
Implementation Method 1
receive depth data generated by a time of flight sensor provided on the user computing device
Data Source
AI summary
A user computing device includes a camera sensor and a depth sensor. Image data generated by the camera captures an image of a user of the user computing device and is provided as an input to a first machine learning model trained to determine a feature set associated with posture of the user from the image data. Depth data generated by the depth sensor contemporaneously with generation of the image data is provided as input to a second machine learning model along with the first feature set to generate a second feature set as an output of the second machine learning model based on the depth data and the first feature set. The posture of the user is determined from the second feature set to provide feedback to the user.