Stationary Radar Ghost-Target Classification With Scene Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing radar systems struggle to accurately distinguish between real targets and ghost targets, particularly in urban environments with multiple reflective surfaces, leading to false positives and the need for user-defined exclusion zones, which degrades usability and fails to handle dynamic changes in the scene.

Innovation Solution

A method utilizing a scene model aggregated over time with information about expected ghost and real target areas, combined with track-specific features, to classify tracks using a classifier module, such as a neural network, to separate real targets from ghost targets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If exclusion areas are defined by user to handle ghost targets, then ghost target detection accuracy is improved, but ease of operation deteriorates

Engineering Contradiction:

Improveghost target detection accuracyVSAvoidease of use

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically generates exclusion areas by detecting reflective surfaces and determining ghost target probabilities without requiring user intervention. The radar system serves itself by autonomously identifying and excluding ghost target regions based on signal reflection characteristics and scene model analysis.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary detection of reflective surfaces and pre-calculates exclusion areas before final target classification. By analyzing signal reflections and building a scene model in advance, the system prepares exclusion zones proactively to prevent ghost target misidentification.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If exclusion areas are added to handle ghost targets, then ghost target detection accuracy is improved, but device complexity increases

Engineering Contradiction:

Improveghost target detection accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system merges multiple functions into a unified processing pipeline: reflective surface detection, ghost target probability calculation, exclusion area generation, and target classification are combined into a single integrated system that operates through coordinated modules rather than separate complex subsystems.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

A scene model serves as an intermediary data structure that aggregates information about reflective surfaces, target probabilities, and spatial relationships. This intermediary layer simplifies the system by providing a standardized representation that feeds into the classification decision without requiring complex direct interactions between all system components.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If exclusion areas are used to handle ghost targets, then ghost target detection accuracy is improved, but adaptability deteriorates

Engineering Contradiction:

Improveghost target detection accuracyVSAvoidadaptability to scene changes

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The exclusion areas are dynamically generated and updated based on real-time detection of reflective surfaces and changing scene conditions. The system continuously monitors for new reflective objects and adjusts exclusion zones accordingly, allowing adaptation to dynamic environments without manual reconfiguration.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system uses feedback from target classification results and scene model updates to refine future exclusion area calculations. By analyzing whether ghost targets were correctly identified and adjusting the scene model accordingly, the system continuously improves its adaptability to changing environments.

Inventive Principle:

Principle #23Feedback

4Device complexity

If traditional radar processing is used, then simplicity is maintained, but measurement precision deteriorates due to false positives

Engineering Contradiction:

Improveprocessing simplicityVSAvoidtarget detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The processing pipeline is segmented into distinct stages: raw radar signal processing, reflective surface detection, ghost target probability calculation, exclusion area generation, and final target classification. This segmentation allows each stage to focus on specific tasks, improving overall precision while maintaining manageable complexity through modular processing.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12411227B2Multipath classification in radar detections

Publication Date: 2025.09.09 AXIS

AI summary

A method for classifying tracks in radar detections of a scene acquired by a stationary radar unit, comprises: acquiring radar detections of the scene using the static radar unit; feeding at least a portion of the radar detections into a tracker module for producing track-specific feature data indicating a specific track in the scene, feeding at least a portion of the radar detections into a scene model comprising information about scene-specific features aggregated over time, and information indicating areas in the scene with expected ghost target detections and areas with expected real target detections, wherein at least a subset of the scene-specific features is determined from the radar detections; classifying the specific track as belonging to a real target or to a ghost target by relating the specific track to a position in the scene model.