Vehicle Ultrasonic-Camera Fusion for Nearby Pedestrian Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing parking assist systems struggle to accurately determine the position of dynamic objects, particularly pedestrians, in the immediate vicinity of a vehicle due to limitations in camera-based estimation and incorrect measurement association with Kalman filters, leading to inaccurate position and motion estimation.

Innovation Solution

A method utilizing ultrasonic sensors and cameras, combined with trained machine recognition methods and a Kalman filter, to continuously determine the approximate position of dynamic objects by correlating ultrasonic measurements with camera images, filtering out static objects, and classifying reflection origin positions based on echo signal properties.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera-based position estimation is used for dynamic objects, then the system can detect objects in the vehicle's vicinity, but the position determination becomes inaccurate for objects within 2 meters due to camera image limitations

Engineering Contradiction:
Improveposition determination accuracyVSAvoiddetection difficulty for nearby objects
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent combines ultrasonic sensor data with camera image data to determine object position. The computing unit correlates echo signal characteristics from ultrasonic sensors with detected objects in camera images, merging acoustic and visual information to achieve accurate position determination for nearby dynamic objects where camera alone fails

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The ultrasonic sensor acts as an intermediary to provide accurate distance measurements for objects in the immediate vicinity. By using echo signal properties as a mediator between the camera detection and final position determination, the system overcomes the camera's limitation in resolving nearby objects

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If Kalman filter is used to track dynamic objects, then continuous position estimation is achieved, but incorrect measurement association leads to inaccurate position and motion estimation

Engineering Contradiction:
Improvetracking reliabilityVSAvoidposition estimation accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The system uses feedback from echo signal characteristics to validate and correct measurements before feeding them into the tracking algorithm. The computing unit continuously monitors ultrasonic echo properties and uses this feedback to confirm correct object-measurement associations, improving the reliability of Kalman filter input data

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary classification and correlation of ultrasonic measurements with camera-detected objects before entering the tracking phase. By pre-associating measurements with correct objects using echo signal characteristics, the system prevents incorrect associations that would otherwise degrade tracking accuracy

Inventive Principle:
Principle #10Preliminary action

3Quantity of substance

If multiple ultrasonic sensors are used to determine reflection origin positions, then distance data can be obtained, but static objects are incorrectly associated with dynamic objects leading to position errors

Engineering Contradiction:
Improvenumber of sensorsVSAvoidobject position accuracy
Core Design Contradiction:
Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent applies different evaluation criteria to different types of objects based on their local characteristics. Dynamic objects are identified by specific echo signal properties such as amplitude changes and temporal patterns, while static objects are filtered out by recognizing their distinct reflection characteristics, allowing accurate differentiation despite using multiple sensors

Inventive Principle:
Principle #3Local quality

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

Enables precise determination of dynamic object positions, especially for pedestrians within 2 meters of the vehicle, improving accuracy and reliability in parking maneuvers by accurately distinguishing between dynamic and static objects.

Implementation Method 1

The sensor data represents, in particular, at least one acquired echo signal corresponding to a transmitted ultrasonic signal between the vehicle and an object in the vicinity of the vehicle

Methodology Applied
Scientific EffectUltrasonic reflection: Echo

Implementation Method 2

The distance is generally determined based on the travel time of a direct and/or indirect echo signal

Methodology Applied
Scientific EffectTime of flight measurement: Time of Flight

Implementation Method 3

at least one camera image is captured by the vehicle camera

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP4296715B1Method for determining an approximate object position of a dynamic object, computer program, device, and vehicle
Publication Date: 2025.12.03 ROBERT BOSCH GMBH
  • EP4296715B1 patent drawingFigure 1
  • EP4296715B1 patent drawingFigure 2
  • EP4296715B1 patent drawingFigure 3~4

AI summary

Method for determining an approximate object position of a dynamic object (1) in the vicinity (90) of a vehicle (100), wherein the vehicle (100) has two ultrasonic sensors (111) and a vehicle camera (121), comprising at least one acquisition (210) of sensor data by means of the two ultrasonic sensors (111); one determination (220) of a current reflection origin position of a static or dynamic object (1, 50, 51) depending on the acquired sensor data; one acquisition (230) of at least one camera image by means of the vehicle camera (121); one detection (240) of the dynamic object (1) depending on the at least one acquired camera image and one determination (250) of a current estimated position of the detected dynamic object (1) relative to the vehicle (100) depending on the acquired camera image;wherein, if a positional distance between the determined estimated position of the detected dynamic object (1) and the determined reflection origin position is less than or equal to a distance threshold, a classification (270) of the current reflection origin position is carried out as belonging to the detected dynamic object (1) depending on the sensor data underlying the determination of the reflection origin position; and the approximate object position of the dynamic object (1) is determined depending on the reflection origin positions classified as belonging to the dynamic object (1).