Vehicle Radar Ghost Object Classification via Track Pairing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Vehicle radar systems face inaccuracies due to multipath reflections, where transmitted energy is deflected by one object and reflected back, causing detection of a ghost object at an incorrect location, leading to potential unnecessary vehicle operations like automatic braking.

Innovation Solution

A method and system that detect and classify tracks of objects in a radar system by identifying candidate pairs, applying criteria such as range difference, reflective surface shape, dynamics correlation, and incident angle to distinguish between true objects and ghost objects, ensuring only true object data is used for vehicle operation control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If radar system detects all reflected energy, then detection coverage is improved, but false ghost object detections increase

Engineering Contradiction:
Improvedetection accuracyVSAvoidghost object detections
Core Design Contradiction:
Measurement precisionVSObject-generated harmful factors

Solution Approach 1:

The patent segments the detection problem by dividing objects into two categories: true objects and ghost objects. It implements separate tracking databases and classification mechanisms for each type, allowing the system to process and analyze reflections differently based on their origin, thereby maintaining detection coverage while eliminating false alarms from multipath reflections

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary classification system that acts as a mediator between raw radar detections and vehicle control actions. This classification mechanism analyzes track patterns, dynamics, and geometric relationships to identify ghost objects before they trigger false vehicle responses, effectively filtering harmful detections while preserving true object information

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If radar system processes all detected objects, then information completeness is improved, but computational complexity increases

Engineering Contradiction:
Improveinformation completenessVSAvoidprocessing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent divides the processing workload by creating separate track databases for true objects and ghost objects. This segmentation allows the system to apply different processing rules and criteria to each category, reducing the computational burden on the overall system while maintaining complete information about both object types

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial processing by focusing computational resources on identifying and classifying ghost objects through specific criteria (dynamics matching, geometric relationships) rather than processing all detected objects uniformly. This selective approach reduces overall computational complexity while maintaining information completeness

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If vehicle responds to all detected objects, then safety response is improved, but unnecessary operations increase

Engineering Contradiction:
Improvesafety responseVSAvoidunnecessary vehicle operations
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent introduces a classification intermediary between object detection and vehicle control that filters out ghost objects before they can trigger unnecessary vehicle operations. This intermediary layer maintains safety responses to true objects while preventing false alarms from multipath reflections, thereby improving reliability by reducing unnecessary operations

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent converts the harmful effect of multipath reflections into a beneficial classification opportunity. By analyzing the characteristic patterns of ghost object reflections (such as geometric relationships with true objects and inconsistent dynamics), the system transforms what was previously harmful noise into useful information for improving safety response accuracy

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

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 differentiates between true and ghost objects, reducing false alarms and improving vehicle operation by correlating ghost objects with their true counterparts, allowing for more precise velocity estimation of true objects.

Implementation Method 1

radio detection and ranging (radar) systems

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

transmitted energy is reflected by an object in the field of view of the radar system

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 3

When transmitted energy is deflected by one object to a second object, the reflected energy received from the second object is referred to as a multipath reflection

Methodology Applied
Scientific EffectMultipath reflection: Reflection

Data Source

PatentUS11587214B2Multipath ghost mitigation in vehicle radar system
Publication Date: 2023.02.21 GM GLOBAL TECHNOLOGY OPERATIONS LLC
  • US11587214B2 patent drawing
  • US11587214B2 patent drawing
  • US11587214B2 patent drawing

AI summary

Systems and methods involve detecting objects using a radar system of a vehicle. Tracks of the objects are initiated in a track database. The tracks store data, respectively, for the objects and are updated based on additional detections of the objects. The tracks of the objects are initially unclassified tracks. Two tracks corresponding to two of the objects are selected as a candidate pair. Criteria are applied to the candidate pair to determine whether one track is of a ghost object and another track is of a true object corresponding with the ghost object. The ghost object represents detection of the true object in an incorrect location. The candidate pair is classified as tracks of a true object and ghost object pair based on determining that the one track is of the ghost object and the other track is of the true object corresponding with the ghost object.