Mouse Displacement Estimation Using Machine Learning Cross-Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer mouse displacement estimation techniques are limited by the precision of optical sensors, leading to inaccurate and discontinuous cursor movement due to false peak cross-correlation values and limited pixel resolution, especially on surfaces with repetitive patterns, which degrades user experience and productivity.
Innovation Solution
A method using a trained machine learning model, such as an artificial neural network, to estimate displacement by analyzing cross-correlation values between images captured by an optical sensor, allowing for sub-pixel precision without increasing sensor resolution, thereby reducing power consumption and chip area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If optical sensor resolution is increased to improve displacement estimation accuracy, then measurement precision improves, but power consumption and chip area increase
Solution Approach 1:
The patent changes the parameter of displacement estimation from direct pixel-based optical sensor measurement to machine learning-based cross-correlation analysis. This allows achieving sub-pixel precision (improving measurement precision) without increasing the physical resolution of the optical sensor, thereby avoiding the associated increase in power consumption and chip area.
Solution Approach 2:
The patent replaces the mechanical/optical measurement system (high-resolution optical sensor) with a computational system (machine learning model analyzing cross-correlation values). This substitution achieves the same measurement precision goal through software intelligence rather than hardware complexity, reducing power consumption and chip area requirements.
2Measurement precision
If optical sensor resolution is increased to improve displacement estimation accuracy, then measurement precision improves, but chip area increases
Solution Approach 1:
The patent transforms the measurement approach from hardware-dependent (optical sensor resolution) to algorithm-dependent (machine learning cross-correlation). This enables achieving high measurement precision without increasing the physical chip area, as the solution resides in software processing rather than hardware expansion.
Solution Approach 2:
The patent substitutes the physical optical measurement system with a computational machine learning system. This replacement achieves sub-pixel displacement precision without requiring additional physical space on the chip, as the intelligence is implemented through software algorithms rather than hardware components.
3Measurement precision
If traditional cross-correlation methods are used for displacement estimation, then device complexity remains low, but measurement precision is limited by pixel resolution
Solution Approach 1:
The patent introduces a machine learning model as an intermediary between the optical sensor data and the displacement estimation result. This intermediary processes the cross-correlation values to achieve sub-pixel precision, bridging the gap between simple optical measurement and high-precision displacement estimation without requiring complex hardware modifications.
Solution Approach 2:
The patent replaces the simple pixel-based displacement calculation with a machine learning-based estimation system. This substitution significantly improves measurement precision by enabling sub-pixel accuracy while managing system complexity through software intelligence rather than hardware complexity.
4Measurement precision
If machine learning model is implemented to achieve sub-pixel precision, then measurement precision improves, but device complexity increases
Solution Approach 1:
The machine learning model serves as an intermediary processing layer that takes cross-correlation values as input and outputs refined sub-pixel displacement estimates. This intermediary approach achieves high measurement precision while keeping the overall system architecture manageable, as it builds upon the existing optical sensor and cross-correlation framework rather than replacing the entire system.
Data Source
AI summary
Methods and systems for determining a displacement of a peripheral device are provided. In one example, a peripheral device comprises: an image sensor, and a hardware processor configured to: control the image sensor to capture a first image of a surface when the peripheral device is at a first location on the surface, the first image comprising a feature of the first location of the surface; execute a trained machine learning model using data derived from the first image to estimate a displacement of the feature between the first image and a reference image captured at a second location of the surface; and determine a displacement of the peripheral device based on the estimated displacement of the feature.