Vehicle Occupant Height Estimation for Adaptive Safety Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current vehicle safety systems rely on basic person detection, which is insufficient for reliably controlling advanced safety measures like airbag deployment and seatbelt functionality, as they do not account for the height or age of occupants, which are crucial for differentiated safety responses, especially for children and adults.

Innovation Solution

A method and system that determine the height of a person in a vehicle by analyzing images from onboard cameras, using bounding boxes and body key points to extract body characteristics, and comparing them to reference data to output control signals for safety measures such as airbag deployment, seatbelt control, and door locks, taking into account the age and height of the occupant.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If basic person detection is used for safety measure control, then the system complexity is low, but the reliability of safety measure control is insufficient

Engineering Contradiction:
Improvereliability of safety measure controlVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the person detection task into multiple analysis stages: initial person detection, body characteristic extraction (bounding boxes and key points), height estimation, and age determination. Each stage processes specific features independently before integrating results for final safety measure control, improving reliability through systematic feature analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediate processing components including body characteristic extractors that generate bounding boxes and key points, height estimation modules that calculate anthropometric parameters, and age determination systems that serve as mediators between raw image data and safety control decisions, enhancing the reliability of the overall system.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If height and age determination is implemented, then the adaptability of safety measures is improved, but the device complexity increases

Engineering Contradiction:
Improveadaptability of safety measuresVSAvoiddevice complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies local quality analysis by extracting specific body characteristics (bounding boxes around body parts, key points at joints and landmarks) rather than treating the person as a single object. This localized feature extraction enables differentiated safety responses based on specific anatomical measurements while maintaining computational efficiency.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent transforms image data into meaningful parameters including sitting height, standing height, age estimates, and body part measurements. These parameter changes convert raw pixel data into actionable anthropometric information that directly informs adaptive safety measure control for different occupant types.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If advanced body characteristic analysis is performed, then the measurement precision of occupant parameters is improved, but the difficulty of detecting and measuring increases

Engineering Contradiction:
Improveprecision of height and age measurementVSAvoiddifficulty of body characteristic detection
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary actions by first detecting the person's presence and generating initial bounding boxes before proceeding to key point identification and height calculation. This staged approach prepares the data structure in advance, making subsequent precise measurements more achievable and reducing the overall detection difficulty.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces complex manual measurement mechanisms with automated computer vision algorithms that use machine learning models to identify key points and calculate anthropometric parameters from images, significantly reducing the difficulty of precise body characteristic detection while maintaining high measurement accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4465257A1Vehicle passenger safety by height estimation
Publication Date: 2024.11.20 APTIV TECHNOLOGIES AG
  • EP4465257A1 patent drawingFigure 1~2
  • EP4465257A1 patent drawingFigure 3A~4
  • EP4465257A1 patent drawingFigure 5~6

AI summary

A computerized method of controlling one or more vehicle safety measures by determining the height of a person sitting on a seat in a vehicle cabin is provided. The method comprises determining, based on one or more images showing the person on a vehicle seat, a height of the person by determining a set of body characteristics of the person, comparing the set of determined body characteristics with a corresponding set of reference characteristics, and determining the height of the person based on the comparison. The method further comprises outputting a control signal to the one or more vehicle safety measures based at least partially on the determined height.