Trajectory Pattern Classification via Normalized Relative Motion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of trajectory-based decision-making increases with the number of objects involved, especially in three-dimensional movements, requiring more computing resources and complicating the tracking of aircraft, satellites, and submersible vehicles compared to surface vehicles.
Innovation Solution
A system that normalizes trajectory data into a reference frame with a constrained movement path for one object, reducing dimensionality and using machine learning classifiers to classify trajectory patterns and initiate responses based on feature data generated from transformed and clustered trajectory data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If trajectory data is processed in three-dimensional space for multiple objects, then tracking accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent transforms three-dimensional trajectory data into two-dimensional relative motion data by establishing a local coordinate system where one object's motion is constrained to a reference axis. This dimensionality reduction maintains the essential relative motion information while significantly reducing computational complexity for processing multiple objects simultaneously.
2Quantity of substance
If the number of objects being tracked increases, then monitoring coverage is improved, but processing time increases
Solution Approach 1:
By converting 3D trajectory processing into 2D relative motion analysis, the patent reduces the computational burden per object pair, enabling faster processing of larger numbers of objects while maintaining comprehensive monitoring coverage.
Solution Approach 2:
The patent extracts only the essential relative motion characteristics between object pairs, discarding redundant absolute position information. This extraction of key features reduces processing requirements and enables faster analysis of multiple objects.
3Measurement precision
If full three-dimensional trajectory data is processed, then classification accuracy is improved, but computational resources required increase
Solution Approach 1:
The patent projects three-dimensional trajectory data onto a two-dimensional plane defined by relative position and bearing angles. This transformation preserves the essential geometric relationships needed for accurate pattern classification while reducing the computational resources required for processing.
Solution Approach 2:
The patent focuses computational resources on analyzing the local relative motion characteristics between object pairs rather than processing complete global trajectory data. This localized analysis approach maintains classification accuracy while reducing overall computational resource requirements.
Data Source
AI summary
A method includes obtaining multiple sets of trajectory data, each descriptive of trajectories of two or more objects (e.g., first and second objects). The method also includes generating transformed trajectory data based on the trajectory data. Each set of transformed trajectory data is descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained. The method further includes generating feature data, performing a clustering operation based on the feature data to generate a set of trajectory clusters, and generating training data based on the set of trajectory clusters. The method further includes using the training data to train a machine learning classifier to classify particular trajectory patterns.