Acoustic Spatial Modelling for Vehicle Interior Object Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for detecting and identifying objects within a vehicle are limited in their ability to accurately determine the presence and location of various objects, including occupants and external items, which can impact safety features and security, particularly in emergency situations.

Innovation Solution

A method and system utilizing wireless signals transmitted by multiple transmitters with known locations, receiving reflection signals, and applying computer vision algorithms to determine a spatial model of the vehicle interior, including multipath propagation components, Doppler shifts, and phase shifts, without the need for cameras, to identify and categorize objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If cameras are used for object detection and spatial modelling, then object identification capability is improved, but device complexity and cost increase

Engineering Contradiction:
Improveobject identification capabilityVSAvoidhardware requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces optical measurement systems (cameras) with acoustic measurement systems (ultrasonic transmitters and receivers). The ultrasonic signals propagate through the vehicle interior, reflect off objects, and return to receivers. By analyzing the time of flight, amplitude, and phase of these reflected signals, the system constructs a spatial model and identifies objects without requiring complex camera hardware or image processing infrastructure.

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

Solution Approach 2:

The ultrasonic measurement system serves multiple functions: it detects object presence, determines object location, categorizes objects (occupant vs. non-occupant), and constructs three-dimensional spatial models. This single acoustic-based system replaces what would traditionally require separate camera systems, lighting, image processing units, and associated hardware, demonstrating multi-functionality that reduces overall system complexity.

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

2Measurement precision

If multiple transmitters and receivers are deployed for accurate spatial modelling, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvespatial model accuracyVSAvoidnumber of components
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple ultrasonic transmitters and receivers into an integrated acoustic measurement network. The transmitters emit ultrasonic signals that propagate through the vehicle interior and reflect off objects. Multiple receivers capture these reflected signals from multiple angles and positions. By merging the data from all transmitters and receivers, the system constructs a comprehensive three-dimensional spatial model with high accuracy, effectively distributing the measurement function across multiple components while maintaining system-level simplicity.

Inventive Principle:
Principle #5Merging (Combining)

3Loss of information

If traditional object detection systems are used, then basic presence detection is achieved, but the ability to identify and categorize objects is limited

Engineering Contradiction:
Improveobject information completenessVSAvoiddetection system capability
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent replaces traditional optical detection systems with an acoustic field-based measurement system. Ultrasonic signals interact with objects in the vehicle interior, and the reflected signals contain information about object location, size, shape, and material properties. By analyzing characteristics such as time of flight, signal amplitude, and phase shifts, the system not only detects object presence but also categorizes objects as occupants or non-occupants and constructs detailed spatial models, significantly reducing information loss about object properties.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach provides a detailed three-dimensional model of the vehicle interior, enhancing safety feature efficiency and warning capabilities for potential hazards, without requiring additional hardware like cameras, and can adapt safety features based on occupant presence and location.

Implementation Method 1

receiving, by a plurality of receivers, a plurality of reflection signals having been reflected in the interior of the vehicle

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 2

determining a source data set by determining multipath propagation components, Doppler shifts, phase shifts and time differences of the received reflection signals

Methodology Applied
Scientific EffectDoppler effect: Doppler Effect

Data Source

PatentEP3392670B1A method and system for spatial modelling of an interior of a vehicle
Publication Date: 2024.06.19 POLESTAR PERFORMANCE
  • EP3392670B1 patent drawingFigure 1~2
  • EP3392670B1 patent drawingFigure 3

AI summary

There is provided a method for spatial modelling of an interior of a vehicle, the method comprising: transmitting a wireless signal, from each of a plurality of transmitters, each transmitter having a known location in the vehicle; receiving, by a plurality of receivers, a plurality of reflection signals having been reflected in the interior of the vehicle, each receiver having a known location in the vehicle; for the received reflection signals, determining a source data set by determining multipath propagation components, Doppler shifts, phase shifts and time differences of the received reflection signals; and determining a spatial model of at least a portion of the vehicle interior by applying a computer vision algorithm on the source data set. There is also provided a system for performing the described method.