Vehicle HMI Gesture Recognition via Spatial Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current human machine interface (HMI) systems in vehicles face challenges such as increased user operation load and manufacturing costs with hard key schemes, unsafe driving with touch screens, and incorrect gesture recognition with gesture recognition schemes, which limit the convenience and safety of controlling multiple electronic devices.

Innovation Solution

An HMI apparatus that recognizes gestures and determines operation commands based on the region where the gesture is performed, allowing for output to the appropriate electronic device, with a control unit identifying the most suitable device for the command and providing guide information for unsuitable commands, thereby minimizing gesture complexity and improving user convenience and safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If hard key scheme is used for input unit, then operation commands can be clearly identified, but physical space requirement increases and manufacturing cost increases

Engineering Contradiction:

Improvecommand identification accuracyVSAvoidphysical space requirement

Core Design Contradiction:

Measurement precisionVSArea of stationary object

Solution Approach 1:

The patent replaces the mechanical hard key system with an optical gesture recognition system. The detection unit captures images of the user's hand gestures, and the control unit processes these images to identify gestures and determine corresponding operation commands. This substitution eliminates the need for physical buttons while maintaining command identification accuracy through image processing and gesture pattern recognition.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Area of stationary object

If touch screen scheme is used for input unit, then physical space is reduced, but driving safety decreases due to manual touching requirement

Engineering Contradiction:

Improvephysical space requirementVSAvoiddriving safety

Core Design Contradiction:

Area of stationary objectVSReliability

Solution Approach 1:

The patent replaces the touch screen's manual interaction requirement with a non-contact gesture recognition system. The detection unit captures hand gestures in the air space above the display, and the control unit translates these gestures into operation commands without requiring physical contact. This allows drivers to control the system while keeping hands on the steering wheel, maintaining safety while reducing physical space requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If gesture recognition scheme is used for input unit, then physical space is reduced and operation load decreases, but command recognition accuracy decreases due to unnatural or unintended gestures

Engineering Contradiction:

Improveuser operation loadVSAvoidgesture recognition accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent divides the display area into multiple predefined regions, each associated with specific operation commands. The detection unit determines which region the gesture is performed in, and the control unit uses both the gesture type and region location to identify the intended command. This segmentation reduces ambiguity by constraining possible commands based on spatial context, improving recognition accuracy while maintaining ease of operation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system provides feedback by displaying guide information that indicates the recognized gesture and the corresponding operation command. This allows the user to verify whether the system correctly interpreted their gesture intent, and if not, to adjust their gesture accordingly. The feedback mechanism helps resolve misrecognition issues by making the system's interpretation transparent to the user.

Inventive Principle:

Principle #23Feedback

4Device complexity

If gesture recognition is performed without region consideration, then operation complexity is reduced, but command determination accuracy decreases

Engineering Contradiction:

Improvegesture system complexityVSAvoidcommand determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the interaction space into multiple regions with distinct command associations. When a gesture is detected, the control unit identifies both the gesture type and the region where it occurred, then determines the operation command based on this combined information. This regional segmentation adds precision to command determination without significantly increasing system complexity, as the region identification is performed automatically through image processing.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10180729B2Human machine interface apparatus for vehicle and methods of controlling the same

Publication Date: 2019.01.15 HYUNDAI MOTOR CO LTD

AI summary

A human machine interface (HMI) minimizing the number of gestures for operation control in which user-intended operation commands are accurately recognized by dividing a vehicle interior into a plurality of regions. The HMI receives an input of a gesture according to each region, and controls any one device according to the gesture. Convenience of a user is improved because the gesture may be performed in a state in which region restriction is minimized by identifying an operation state and an operation pattern of an electronic device designated according to each region to recognize the user's intention when the user performs the gesture in a boundary portion between two regions or even in multiple regions.