Adaptive Threshold Object Matching in Collaborative Perception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In vehicle-to-vehicle communication, accurately identifying corresponding objects across multiple messages is challenging due to uncertainties in object locations, leading to false positives even with single adaptive thresholds.
Innovation Solution
The use of multiple adaptive thresholds based on uncertainties of different parameters, such as location and heading, to filter out false positives and improve object correspondence identification in collaborative perception messages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single adaptive threshold is used to match objects in collaborative perception messages, then the matching process is simple and fast, but false positives occur due to uncertainty in object locations
Solution Approach 1:
The patent divides the single threshold into multiple adaptive thresholds corresponding to different parameters (location, heading, velocity). Each parameter has its own threshold calculated based on its specific uncertainty, allowing selective filtering of false positives without requiring a complex unified threshold model
Solution Approach 2:
The patent transitions from a single-dimensional threshold approach to a multi-dimensional approach by introducing multiple parameters (location, heading, velocity) each with its own adaptive threshold. This dimensional expansion enables more comprehensive false positive filtering while maintaining computational efficiency through independent threshold calculations
2Measurement precision
If multiple adaptive thresholds based on different parameters are used, then false positives are reduced and matching accuracy is improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent pre-calculates uncertainty values for each parameter (location, heading, velocity) from the collaborative perception messages before threshold computation. This preliminary preparation of uncertainty data enables rapid threshold calculation and filtering operations, reducing overall processing time while maintaining high matching accuracy
Solution Approach 2:
The patent dynamically adjusts multiple parameters (location uncertainty, heading uncertainty, velocity uncertainty) to generate corresponding adaptive thresholds. By changing and optimizing these parameters based on actual message data, the system achieves high measurement precision while keeping processing efficient through parameter-driven threshold adaptation
Data Source
AI summary
A method includes calculating a first adaptive threshold based on uncertainty of a first parameter of a first collaborative perception message (CPM) from a first node and uncertainty of the first parameter of a second CPM from a second node, calculating a second adaptive threshold based on uncertainty of a second parameter of the first CPM and uncertainty of the second parameter of the second CPM, obtaining a first association matrix by filtering out one or more pairs whose score is greater than the first adaptive threshold, obtaining a second association matrix by filtering out one or more pairs whose score is greater than the second adaptive threshold, obtaining a fused association matrix based on the first association matrix and the second association matrix, and implementing a fusion algorithm on the fused associated matrix to obtain correspondence identification among objects.