Multi-Sensor Airspace Track Correlation Using Density Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing air traffic control systems face challenges in accurately correlating airspace surveillance data from multiple sensors due to measurement uncertainty and instrument errors, leading to unclear object positions and cluttered displays.
Innovation Solution
A method and apparatus that receive and aggregate surveillance data from multiple sensors, perform density-based clustering, determine candidate associations between tracks and clusters, and estimate a single track for each target based on these associations, using techniques like DBSCAN and Kalman filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple sensors are used to track aerial vehicles, then coverage and detection capability are improved, but measurement uncertainty and position accuracy deteriorate due to instrument error and different sensor reports
Solution Approach 1:
The patent combines surveillance data from multiple independent sensors by performing density-based clustering on aggregated track data. The system merges tracks from different sensors that correspond to the same target by identifying spatial and temporal correlations, then fuses these tracks to produce a single correlated track with improved position accuracy despite individual sensor uncertainties.
2Quantity of substance
If multiple sensors independently track objects, then detection capability is improved, but data complexity and processing difficulty increase due to multiple independent tracks per target
Solution Approach 1:
The patent segments the complex task of multi-sensor correlation into distinct processing stages: data aggregation from multiple sensors, density-based clustering of aggregated data to identify potential target groups, candidate association determination between tracks and clusters, and final track estimation. This segmentation transforms an intractable complex problem into a sequence of manageable processing steps.
Solution Approach 2:
The patent introduces density-based clustering as an intermediary processing step between raw sensor data and final target identification. The clustering algorithm creates intermediate cluster representations that bridge the gap between multiple independent sensor tracks and the underlying physical targets, making the correlation problem more tractable by grouping related tracks before final association.
3Adaptability or versatility
If each sensor reports object positions independently, then sensor autonomy is maintained, but situational awareness deteriorates due to unclear actual object positions
Solution Approach 1:
The patent implements a feedback mechanism where the system correlates sensor data by comparing tracks from multiple sensors, identifies discrepancies due to measurement uncertainty, and produces corrected position estimates through track fusion. The correlated track information feeds back into the surveillance system, providing clarified object positions that resolve the uncertainty introduced by independent sensor reporting.
Data Source
AI summary
A method may comprise receiving airspace surveillance data from a plurality of sensors, the airspace surveillance data comprising tracks associated with one or more targets, aggregating the airspace surveillance data to obtain aggregated data, performing density-based clustering of the aggregated data to obtain a plurality of clusters, determining one or more candidate associations between the tracks and the clusters, associating each of the tracks with one of the one or more targets based on the candidate associations, and estimating a track for each of the one or more targets based on the associations between the tracks and the one or more targets.