Seat Belt Detection Using Shoulder Line Intersection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing cabin monitoring systems using image sensors are not sufficiently accurate in determining if a vehicle occupant is correctly wearing a seat belt, often requiring extensive processing power and struggling with contrast issues between the seatbelt and clothing.

Innovation Solution

A computer-implemented method and system that acquires an image of the occupant, identifies the shoulders and seatbelt, and determines the intersection between the seatbelt and a line connecting the shoulders to assess if the seatbelt is correctly applied, utilizing image processing techniques like edge detection and human pose estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image data is used to determine seat belt position, then measurement capability is improved, but measurement precision is insufficient

Engineering Contradiction:
Improveseat belt position detection accuracyVSAvoiddetection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent segments the seat belt detection task into multiple components: detecting the shoulder line, detecting the seat belt longitudinal extension separately, and then determining their intersection. This segmentation allows each detection task to be optimized independently, improving overall measurement precision while maintaining reliability through multiple verification points

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary geometric construct - the intersection point between the shoulder line and seat belt longitudinal extension. This intersection point serves as a mediator that translates image data into a reliable positional indicator, enhancing both measurement precision and detection reliability by providing a clear geometric reference

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If complex image processing is used to improve detection accuracy, then measurement precision is improved, but processing power requirements increase

Engineering Contradiction:
Improveseat belt detection accuracyVSAvoidprocessing power consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the essential geometric features needed for seat belt detection - specifically the shoulder line and seat belt longitudinal extension - from the full image data. By taking out only these critical elements rather than processing the entire image, the system achieves good measurement precision with significantly reduced processing power requirements

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial action by focusing detection efforts only on the relevant portions of the image (shoulder area and seat belt area) rather than analyzing the entire image. This selective approach maintains detection accuracy while minimizing processing power consumption by avoiding unnecessary analysis of irrelevant image regions

Inventive Principle:
Principle #16Partial or excessive action

3Use of energy by moving object

If simple image processing is used, then processing power is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improveprocessing power efficiencyVSAvoidseat belt position accuracy
Core Design Contradiction:
Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The patent performs preliminary action by first detecting the shoulder line and seat belt longitudinal extension separately before determining their intersection. This preliminary detection of key geometric features enables the use of simpler processing in the final intersection calculation, maintaining measurement precision while improving processing power efficiency through staged simplification

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4358040A1Seat belt detection
Publication Date: 2024.04.24 SMART EYE AB
  • EP4358040A1 patent drawingFigure 1~2
  • EP4358040A1 patent drawingFigure 3~4a
  • EP4358040A1 patent drawingFigure 4b~4c

AI summary

A system and method for determining if an occupant of a vehicle has correctly applied a seat belt by acquiring an image of the occupant, the image including at least a shoulder portion of the occupant, identifying left and right shoulders and a longitudinal extension of a seat belt in the image, determining an intersection between the longitudinal extension and a line connecting the left and right shoulders, and, based on a relative position of the intersection and the shoulders, deducing whether the seat belt is correctly applied.