Vehicle Radar Object Recognition for Stationary Object Misclassification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object recognition technologies in vehicle radar sensors often misidentify stationary objects like tunnel vents as moving objects due to the Doppler effect, leading to inaccurate elevation information and potential misclassification, which can trigger unnecessary ADAS interventions.

Innovation Solution

An object recognition apparatus and method that utilizes in-vehicle sensors to calculate distance errors and categorize objects based on these errors, employing a condition determining section, an estimator, a calculator, and a determining section to differentiate between specific and normal objects using distance difference information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If radar sensors are used to detect objects during driving, then object recognition capability is improved, but measurement precision deteriorates due to misidentification of stationary objects as moving objects

Engineering Contradiction:

Improveobject recognition capabilityVSAvoidelevation information accuracy

Core Design Contradiction:

Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The system continuously monitors the distance difference between consecutive radar measurements and uses this feedback to determine object category. When the distance difference exceeds a threshold, the system identifies the object as stationary and adjusts the elevation information accordingly, preventing misidentification of stationary objects like tunnel vents as moving objects.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system changes the parameter used for object classification from solely Doppler-based velocity detection to a combined approach that includes distance difference calculation. By introducing distance difference as a new classification parameter, the system can distinguish between stationary and moving objects more accurately, resolving the measurement precision issue.

Inventive Principle:

Principle #35Parameter changes

2Speed

If radar sensors detect objects using Doppler effect, then speed measurement is improved, but reliability deteriorates due to false detection of stationary objects as moving objects

Engineering Contradiction:

Improveobject speed detectionVSAvoidobject classification accuracy

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system introduces distance difference information as an intermediary parameter that mediates between the radar's speed detection capability and the need for reliable object classification. This intermediary helps filter out false positives by comparing consecutive distance measurements before final classification.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces the purely mechanical/Doppler-based speed detection mechanism with an electronic processing approach that calculates distance differences and uses threshold comparison. This substitution allows the system to maintain speed detection capability while adding a layer of verification that improves reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Extent of automation

If ADAS control is activated based on radar detection, then vehicle control functionality is improved, but harmful factors increase due to unnecessary interventions caused by misidentification

Engineering Contradiction:

ImproveADAS control functionalityVSAvoidfalse ADAS interventions

Core Design Contradiction:

Extent of automationVSObject-generated harmful factors

Solution Approach 1:

The system performs preliminary classification of objects into stationary or moving categories before activating ADAS control. By pre-determining the object type using distance difference calculation, the system prevents unnecessary ADAS interventions from being triggered by misidentified stationary objects, thereby reducing harmful false actions.

Inventive Principle:

Principle #10Preliminary action

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

Accurately distinguishes between stationary objects and moving objects, enhancing the reliability of ADAS systems by reducing false detections and improving vehicle control.

Implementation Method 1

receiving first sensing information and, after a predetermined time, second sensing information from a radar sensor

Methodology Applied

Scientific EffectRadar: Radar

Implementation Method 2

determining whether a predetermined condition is satisfied based on position information detected by a position detection sensor

Methodology Applied

Scientific EffectGPS:

Data Source

PatentUS20250347776A1Object recognition apparatus and method

Publication Date: 2025.11.13 HL KLEMOVE CORP

AI summary

An object recognition apparatus and method. If a predetermined condition is satisfied based on position information detected by a position detection sensor and normal operation information of the position detection sensor, a determining section categorizes an object candidate as one of a specific object or a normal object based on first sensing information and, after a predetermined time, second sensing information received from a radar sensor.