Mobile Object Tracking with Visibility-Weighted Nonlinear Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tracking technologies for mobile objects face accuracy issues when partial observation from external field sensor systems is difficult, leading to deviations in estimated state values and reduced tracking precision.
Innovation Solution
A tracking device and method that utilize nonlinear filtering to estimate state values by setting weighting factors for vertices in a rectangle model based on visibility from external field sensors, acquiring observation errors, and calculating covariance, thereby reflecting visual recognition degrees to improve tracking accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If nonlinear filtering with visibility-based weighting is implemented, then tracking precision is improved, but device complexity increases
Solution Approach 1:
The patent applies local quality by assigning different weighting factors to different vertices of the rectangle model based on their individual visibility conditions. Each vertex is evaluated independently for visibility from external field sensors, and vertices with better visibility receive higher weights in the state value estimation. This localized differentiation of quality metrics resolves the contradiction by improving tracking precision through selective weighting without requiring complete system redesign.
Solution Approach 2:
The patent changes the parameter of vertex visibility by calculating visibility-based weighting factors for each vertex and using these as dynamic parameters in the nonlinear filtering process. By transforming the static rectangle model into a dynamic weighted system where vertex importance varies based on observational conditions, the patent improves tracking precision while managing complexity through parameter optimization rather than structural expansion.
2Measurement precision
If visibility-based weighting factors are calculated for each vertex, then state value estimation accuracy is improved, but computational load increases
Solution Approach 1:
The patent segments the mobile object into multiple vertices of a rectangle model, allowing independent visibility assessment and weighting for each vertex. This segmentation enables parallel computation of visibility factors for different vertices, improving state value estimation accuracy through granular analysis while managing computational load through distributed processing of vertex evaluations.
Solution Approach 2:
The patent applies partial action by focusing computational resources on calculating visibility weights only for vertices that are partially or fully visible from external sensors. Vertices that are completely occluded or irrelevant to current observation can be excluded from detailed weighting calculations, thereby improving estimation accuracy for observable regions while reducing unnecessary computational expenditure on invisible portions.
Data Source
AI summary
By a tracking device, a tracking method, or a computer-readable non-transitory storage medium storing a tracking program, a state value of a mobile object is estimated to track the mobile object, the observation value of the mobile object observed at an observation time is acquired, a prediction state value is acquired, a true value of the state value at the observation time is estimated by nonlinear filtering.