Vehicle Position Calculation Using Map-Image Correlation and User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing position calculating apparatuses for host vehicles face errors in calculating vehicle position due to insufficient map information, road changes, blurred lane markings, wet roads, puddles, and shadows, leading to incorrect position recognition.
Innovation Solution
A position calculating apparatus that includes a detector to gather surrounding environment data, a calculator to extract and compare maps with images, and a corrector to adjust the vehicle's position and direction based on user input, using frequency analysis and correlation methods to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map information and surrounding images are compared to calculate vehicle position, then position accuracy is improved, but erroneous recognition occurs when map information is insufficient or road conditions change
Solution Approach 1:
The system displays the calculated position and direction to the user and accepts correction inputs. When the user provides correction input, the system updates the position and direction calculations. This feedback loop allows the system to learn from user corrections and improve its accuracy over time, resolving the contradiction between achieving high position accuracy and avoiding erroneous recognition.
Solution Approach 2:
The system performs frequency analysis on the surrounding image to generate a correlation image before final position calculation. By preprocessing the image data and identifying potential position candidates through correlation analysis, the system prepares multiple possible solutions in advance, then uses user feedback to select the correct one, thereby improving both accuracy and reliability.
2Productivity
If automated position calculation is performed without user intervention, then productivity is improved, but measurement precision deteriorates due to erroneous recognition
Solution Approach 1:
The system introduces a correlation image as an intermediary representation between the raw surrounding image and the final position calculation. The correlation image highlights potential position matches through frequency analysis, making the automated calculation more robust. This intermediary step allows the system to process positions automatically while maintaining higher precision by visualizing confidence levels for different position candidates.
Data Source
AI summary
A position calculating apparatus is provided with: an acquirer configured to obtain a position of a host vehicle; a detector configured to detect surrounding environment including structures around the host vehicle; a calculator configured to extract a map of surroundings of the host vehicle on the basis of the obtained position, configured to compare the extracted map with a surrounding image based on the detected surrounding environment, and configured to calculate a position and a direction of the host vehicle on the extracted map; a display device configured to superimpose and display the extracted map on the surrounding image on the basis of the calculated position and the calculated direction; and a corrector configured to correct the calculated position and the calculated direction with reference to a inputted correction instruction if the correction instruction is inputted through an input device.