Steering Wheel Hand Detection Using 3D Image Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for determining whether a vehicle driver's hands are on the steering wheel are prone to false positives due to detection by other body parts or objects, lacking the ability to reliably distinguish hands from other elements.

Innovation Solution

A computer-implemented method using cameras to capture and process three-dimensional image data, allowing for the determination of hand cooperation with the steering element by analyzing pixel values and employing algorithms like particle filters and neural networks to differentiate hands from other objects and body parts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If capacitive sensors or torque sensors inside the steering wheel are used to detect hand contact, then the system can detect human hands touching the steering wheel or force applied, but false positives occur when other objects or body parts contact the wheel

Engineering Contradiction:
Improvehand detection accuracyVSAvoidfalse positive rate
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent introduces an intermediary classification system that processes sensor signals before final detection. Multiple sensor types (capacitive, torque, pressure) are combined and processed through classification algorithms that distinguish hand characteristics from other objects or body parts, reducing false positives while maintaining detection sensitivity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically adjusts detection parameters such as sensitivity thresholds, capacitance ranges, and torque thresholds based on driving conditions and sensor calibration. This allows the system to adapt to different scenarios and reduce false detections while maintaining accurate hand detection across varying operational contexts

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If gesture tracking or body posture measurement systems are used to monitor driver hands, then hand position can be tracked, but the systems cannot reliably distinguish hands from other body parts or objects

Engineering Contradiction:
Improvehand position tracking accuracyVSAvoidhand identification complexity
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The detection system divides the monitoring task into multiple independent sensor channels (capacitive sensing, torque sensing, pressure sensing) that each provide specific information. By segmenting the detection function across multiple sensor types, the system can cross-validate signals and accurately identify hands while filtering out other body parts or objects

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs a multi-functional sensor system where the same sensor array serves multiple detection purposes: hand presence detection, hand position tracking, and hand identification. This universal approach allows a single system to perform multiple functions that would otherwise require separate systems, improving both accuracy and efficiency

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3719697B1Method and device for determining whether a hand cooperates with a manual steering element of a vehicle
Publication Date: 2023.10.18 APTIV TECHNOLOGIES LTD
  • EP3719697B1 patent drawingFigure 1
  • EP3719697B1 patent drawingFigure 2a
  • EP3719697B1 patent drawingFigure 2b

AI summary

A computer-implemented method for determining an information on whether at least one hand of a vehicle driver cooperates with a manual steering element of a vehicle, wherein the method comprises: taking at least one image by means of at least one sensor mounted on the vehicle, wherein the at least one image captures at least a manual steering element of the vehicle; and determining, on the basis of the at least one image, an information on whether at least one hand of a vehicle driver cooperates with the manual steering element.