Object Tracking Contour Association for Accurate Target Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing extended object tracking systems suffer from inaccuracies due to incorrect associations between prediction values and observed values, leading to decreased accuracy in estimating the position of targets.
Innovation Solution
An object tracking device that includes a sensor part, a contour calculator, a prediction value calculator, an association section, and an estimation section, which calculates multiple prediction values independently from observed values and associates them with multiple observed values to form association sets, thereby suppressing incorrect associations and improving estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If prediction values are calculated based on observed values, then the association process is simplified, but incorrect associations occur leading to decreased estimation accuracy
Solution Approach 1:
The patent divides the calculation process into two independent stages: first calculating prediction values solely from the predicted contour and shape model, then separately performing the association with observed values. This segmentation prevents the propagation of errors that would occur if prediction values were directly derived from observed values, thereby maintaining estimation accuracy while preserving association simplicity.
Solution Approach 2:
The patent performs the calculation of prediction values as a preliminary action before the association process. By pre-calculating prediction values based on the predicted contour and shape model independently of observed values, the system prepares accurate reference points in advance that can be reliably associated with observed values without introducing circular dependency errors.
2Measurement precision
If multiple prediction values are calculated independently from observed values, then incorrect associations are suppressed improving accuracy, but the calculation complexity increases
Solution Approach 1:
The patent segments the complex calculation into two distinct modules: a prediction value calculation module that operates independently on the predicted contour and shape model, and an association module that matches prediction values with observed values. This modular segmentation reduces overall system complexity despite generating multiple prediction values, as each module has a clearly defined and simplified function.
Solution Approach 2:
The patent changes the computational parameters by deriving prediction values from geometric parameters (predicted contour and shape model) rather than directly from measurement parameters (observed values). This parameter transformation approach maintains accuracy by using independent geometric constraints while the structured association process manages the increased number of prediction values efficiently.
Data Source
AI summary
An object tracking device according to one aspect of the present disclosure includes a sensor part, a contour calculator, a prediction value calculator, an association section, and an estimation section. The contour calculator calculates a predicted contour based on a predetermined shape model of an object and an estimation value calculated in the past. The prediction value calculator calculates a plurality of prediction values located in a prescribed region on and/or in the predicted contour, independently from a plurality of observed values acquired.