Driver-Guided Sensor Alignment for Outside-Vehicle Object Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle sensor systems struggle to accurately and efficiently detect and prioritize objects of interest outside the vehicle, particularly in complex environments or when sensor data is ambiguous, leading to potential false detections and reduced system robustness.

Innovation Solution

The method involves recording and analyzing the gaze direction of a vehicle occupant, especially the driver, to determine an area of interest outside the vehicle, spatially aligning sensors to this area, and using a confidence value based on gaze duration and frequency to enhance detection precision and reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If sensor data from multiple sensors is aggregated to improve detection quality and reliability, then detection accuracy and reliability are improved, but device complexity and data processing requirements increase

Engineering Contradiction:
Improvedetection reliabilityVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the detection task by dividing the environment into multiple regions of interest (ROIs) based on gaze direction analysis. Instead of processing all sensor data uniformly, the system focuses computational resources on specific spatial segments where objects are most relevant to the driver, thereby maintaining high detection reliability while reducing overall system complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by enhancing detection precision in specific regions of interest identified through gaze analysis. The system allocates higher processing priority and more sophisticated detection algorithms to ROIs where the driver is looking, while using simpler detection methods in other areas, thus achieving high reliability where needed without uniformly increasing system complexity.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If regions of interest are defined to reduce false detections and accelerate decision-making, then detection precision and response time are improved, but initial setup complexity and tracking difficulty increase

Engineering Contradiction:
Improveobject detection precisionVSAvoidROI tracking complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by pre-defining regions of interest based on driver gaze direction before object detection begins. The system analyzes where the driver is looking and pre-establishes ROIs in those areas, so that when objects appear in these regions, detection can immediately begin with high precision without requiring complex real-time tracking setup.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses the driver's own gaze direction as a natural guide to automatically define regions of interest, eliminating the need for manual ROI configuration or complex algorithmic determination. The driver's attention naturally identifies what regions are important, and the system adapts to this self-provided information, simplifying the ROI management process.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If gaze direction analysis is used to determine areas of interest and align sensors, then object identification accuracy is improved, but system complexity and processing time increase

Engineering Contradiction:
Improveobject identification accuracyVSAvoidgaze analysis processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements periodic action by updating gaze direction analysis and region of interest definition at specific time intervals rather than continuously. The system samples driver gaze at regular periods, determines ROIs based on these samples, and maintains these regions between updates. This periodic approach achieves good object identification accuracy while significantly reducing processing time compared to continuous analysis.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3622709B1Method and apparatus for the spatially resolved detection of an object outside a vehicle with the aid of a sensor installed in a vehicle
Publication Date: 2025.11.05 VOLKSWAGEN AG
  • EP3622709B1 patent drawingFigure 1
  • EP3622709B1 patent drawingFigure 2
  • EP3622709B1 patent drawingFigure 3

AI summary

In the method according to the invention for the spatially resolved detection of an object (6, 7, 8) outside a vehicle with the aid of a sensor (9, 10, 11) installed in a vehicle, the viewing direction of a vehicle occupant is captured (1). The captured viewing direction is analysed (2) over a period and a region of interest (ROI) outside the vehicle is determined (2) therefrom. The sensor (9, 10, 11) is then spatially sensitized and/or oriented (3) in the direction of the determined region of interest (ROI).