Vehicle-Captured Map Generation with Bias-Weighted Data Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional map generation systems face accuracy issues when the number of probe data is small due to bias in data transmitted from vehicle-mounted cameras, leading to decreased map generation accuracy.
Innovation Solution
A map system that includes a vehicle apparatus with an imaging sensor and a server with an integrating unit that weights and integrates data based on bias, improving accuracy by preferentially using data with higher estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data from multiple vehicle apparatuses are integrated without weighting, then the quantity of data increases, but map generation accuracy decreases due to bias in the data
Solution Approach 1:
The patent applies local quality by assigning different weights to different data sources based on their individual characteristics and reliability. Each vehicle apparatus's data is evaluated for bias and given a corresponding weight, allowing high-quality data to contribute more to the integrated map while low-quality data contributes less, thus maintaining accuracy while integrating diverse data sources
Solution Approach 2:
The patent changes the parameter of data weighting by introducing weight values that reflect the reliability and bias characteristics of each data source. This parameter transformation allows the system to dynamically adjust the contribution of each data source, converting unweighted data integration into weighted integration that preserves accuracy
2Measurement precision
If data weighting based on bias is implemented, then map generation accuracy improves, but the complexity of the integrating unit increases
Solution Approach 1:
The integrating unit performs self-service by automatically evaluating the bias characteristics of incoming data and assigning weights without requiring external intervention. The system autonomously calculates weight values based on predefined criteria related to data quality and bias, reducing the need for manual calibration while maintaining high map generation accuracy
Data Source
AI summary
A map system includes a vehicle apparatus that is mounted to a vehicle. The map system includes an imaging apparatus, a server, and an integrating unit. The imaging apparatus captures an image of a surrounding area of the vehicle. The server generates a map using data that corresponds to feature points extracted from the image captured by the imaging apparatus that is transmitted from the vehicle apparatus. The integrating unit weights the pieces of data that are transmitted from a plurality of vehicle apparatuses based on bias in the pieces of data and generates a map by integrating at least a portion of the plurality of pieces of data based on the weighting.