Object Recognition Device Dynamic Association Reference Values
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional object recognition devices face misrecognition issues due to positional deviations between sensors of different types or with varying resolutions, leading to incorrect identification of detection data from the same object as different objects, especially at increasing distances.
Innovation Solution
An object recognition device that integrates data from multiple sensors using a data reception unit, association processing unit, and updating processing unit to create observation data and association data, prioritizing the latest association data from the same sensor to update object data and reduce positional deviations by using association reference values and state vectors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If sensors of different types (e.g., radio wave radar and optical camera) are used for object detection, then the coverage and detection capabilities are improved, but positional deviations occur between sensors that increase with distance and cause misrecognition
Solution Approach 1:
The patent changes the parameter of association reference values from static bias error assumptions to dynamic values that vary according to detection distance and sensor type. This allows the system to adapt the association criteria to the specific conditions of each detection scenario, resolving the contradiction between using diverse sensors and maintaining position recognition accuracy.
Solution Approach 2:
The system transitions from a static coordinate offset correction model to a dynamic association mechanism that continuously adapts based on detection distance, sensor characteristics, and object properties. This dynamic approach allows the system to maintain accurate object identification despite varying positional deviations between different sensor types.
2Reliability
If coordinate offset correction based on bias error estimation is applied, then recognition of detection data from multiple sensors as same object is improved, but misrecognition occurs when positional deviation is not constant but varies with distance and sensor type
Solution Approach 1:
The patent changes the association reference values dynamically based on detection distance and sensor characteristics, rather than using fixed bias error corrections. This allows the system to maintain reliable object recognition even when positional deviations vary with distance and sensor type, resolving the contradiction between recognition reliability and position accuracy.
3Measurement precision
If association reference values are updated using latest association data from the same sensor, then object recognition precision is improved, but system complexity increases due to additional processing requirements
Solution Approach 1:
The system creates and maintains association reference values as simplified representations of sensor-specific detection characteristics. These reference values act as copies or proxies that capture the essential association patterns without requiring complex real-time calculations, thus improving recognition precision while limiting the increase in processing complexity.
Data Source
AI summary
An object recognition device 4 includes: a data reception unit 5 that creates observation data of respective sensors 1, 2 in accordance with sensor's detection data of an object in the surroundings of a host vehicle; an association processing unit 6 which, based on an association reference value, generates association data denoting a correspondence between the observation data and object data of a previous process cycle; and an updating processing unit 7 which, based on the association data, updates a state vector included in the object data of the previous process cycle, and updates the object data by including latest association data being the observation data having corresponded to the object data most recently, wherein the association processing unit 6 generates the association reference value using preferentially the latest association data of the same sensor as that of the observation data of a current process cycle.