Vehicle Detection Point Association Using Blur Zone Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assessing the association of a detection point with an object in a motor vehicle's surroundings are imprecise, leading to inaccuracies in object evaluation and information provision, particularly affecting free space assessment and map integration.
Innovation Solution
A method that forms a blurred zone around detected points, using additional detection points to assess association, with a covariance matrix and Mahalanobis distance calculation to determine if points lie within an overall blurring zone, allowing for more precise object assignment and fusion of data from different sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single detection point is used to assess object association, then the evaluation process is simple, but the assessment accuracy is limited and inaccurate
Solution Approach 1:
The patent combines multiple detection points (first detection point and second detection point) to form a comprehensive assessment basis. By merging the information from multiple detection points and their respective blur zones, the system achieves more accurate object association assessment than using a single detection point would provide.
Solution Approach 2:
The patent introduces an overall blur zone as an intermediary construct that mediates between individual detection points and object association determination. This overall blur zone serves as a computational tool that integrates the positional uncertainties of multiple detection points to enable more accurate assessment.
2Loss of information
If general object interface information is provided, then data sharing between systems is enabled, but the information is poorly specified and lacks detail
Solution Approach 1:
The patent enhances the general object interface by adding locally specific quality information - namely, the blur zone characteristics for each detection point. This allows the interface to maintain its general structure for system compatibility while incorporating detailed local uncertainty information that improves assessment accuracy.
3Measurement precision
If multiple detection points and blur zones are considered, then assessment accuracy improves, but the evaluation effort and computational complexity increase
Solution Approach 1:
The patent performs preliminary actions by pre-defining the blur zones around each detection point based on sensor characteristics and detection conditions. This preliminary characterization of uncertainty allows for more efficient real-time evaluation, as the computationally intensive blur zone calculations are performed in advance rather than during the actual assessment process.
Data Source
Figure 1
Figure 2~4
AI summary
The invention relates to a method for assessing an association of a detection point (12, 13, 19, 20) with an object in a surrounding area (7, 8) of a motor vehicle (1), in which the detection point (12, 13, 19, 20) is detected by means of a first sensor device (4) of the motor vehicle (1), and a blur zone (14, 15) around the detection point (12, 13, 19, 20) characterizing a position blur of the detection point (12, 13, 19, 20) is formed. For the assessment of the association of the detection point (12, 13, 19, 20) with the object, at least one position of an additional detection point (12, 13, 19, 20) of the object is taken into consideration, wherein a total blur zone (16) is formed subject to the blur zone (14, 15) of the detection point (12, 13, 19, 20), and the association of the detection point (12, 13, 19, 20) with the object is accorded when the detection point (12, 13, 19, 20) and the additional detection point (12, 13, 19, 20) are in an area formed by the total blur zone (16). The invention further relates to a driver assistance system (2) and to a motor vehicle (1).