Track Crossover Management for Mobile Object Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing object tracking systems face challenges in managing ambiguities during crossings of similar objects, leading to potential mix-ups and decreased tracking quality due to difficulties in distinguishing between objects based on sensor measurements.

Innovation Solution

A method for managing track crossings involves a recursive filter and ambiguity notification, using specific relationships and thresholds to determine unambiguous tracks and apply weighted sums for estimation, thereby reducing the impact of ambiguities on tracking accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If standard tracking methods (NN or GNN processing) are used to group measurements from multiple sensors, then tracking can be maintained under normal conditions, but during track crossings of similar objects, measurements become ambiguous and may be attributed to faulty tracks, leading to mix-ups and decreased tracking quality

Engineering Contradiction:
Improvetracking accuracyVSAvoidmeasurement distinction
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by detecting track crossings before they cause measurement ambiguities. The system monitors track trajectories and identifies potential crossing events in advance, allowing the tracking algorithm to switch to a specialized crossing-handling mode that prevents measurements from being incorrectly attributed to the wrong track, thereby maintaining tracking reliability during critical crossing periods

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes tracking parameters dynamically based on track proximity and crossing detection. When tracks are detected to be approaching or crossing, the system adjusts association parameters such as gate sizes, measurement weighting, and track selection criteria to disambiguate measurements. This parameter adaptation allows the system to maintain measurement precision during crossings by using different association rules when tracks are close versus when they are well-separated

Inventive Principle:
Principle #35Parameter changes

2Area of stationary object

If the sensor field of view is increased to monitor more objects, then coverage is improved, but ambiguities during crossings increase and tracking quality decreases

Engineering Contradiction:
Improvesensor coverage areaVSAvoidtracking reliability
Core Design Contradiction:
Area of stationary objectVSReliability

Solution Approach 1:

The patent applies segmentation by dividing the sensor field of view into multiple sectors or zones, each monitored by dedicated track management logic. When tracks cross in one sector, the system can independently handle the ambiguity locally without affecting tracking reliability in other sectors. This spatial segmentation allows wide coverage while maintaining reliable tracking by isolating crossing ambiguities to specific regions

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary detection of track crossings by analyzing track trajectories and predicting future positions. When a crossing is detected or predicted in a particular sector, the system proactively adjusts measurement association rules for that sector before ambiguities occur, allowing the sensor to maintain wide coverage while preserving tracking reliability through localized parameter adjustments

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3189348B1Method for managing crossovers in the tracking of mobile objects, and associated device
Publication Date: 2020.01.01 THALES SA
  • EP3189348B1 patent drawingFigure 1~2
  • EP3189348B1 patent drawingFigure 3
  • EP3189348B1 patent drawing

AI summary

The invention relates to a method for managing track crossovers, and to a device for monitoring mobile objects, suitable for implementing said method. The method for managing track crossovers comprises, for each track, at a given moment, a test step (Step 1) for determining whether the given track is ambiguous or not at the given moment, and in the event that it is, a step (Step 2) for the specific processing of the estimation of the track.