Parking Map Feature Selection for Accurate Automatic Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking assistance technologies fail to consider the varying accuracy requirements based on the angle with respect to the optical axis of a camera, the difference in height between feature points and the camera, and the differing accuracy needs between the front-rear and left-right directions, leading to potential position accuracy issues during automatic parking.
Innovation Solution
A parking assistance apparatus that includes an image acquirer, a feature point detector, a feature point selector, and a vehicle controller. The feature point selector evaluates feature points during learning travel to prioritize their registration on a map based on their position, angle with respect to the camera's optical axis, and relative position, thereby improving position accuracy during automatic parking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If feature points are registered uniformly across all positions on the map, then the map contains sufficient feature points for position estimation, but the position accuracy deteriorates because feature points far from the parking position and at unfavorable angles are registered alongside critical feature points
Solution Approach 1:
The patent applies local quality by differentiating the registration criteria for feature points based on their spatial location and angular relationship to the vehicle. Feature points are selectively registered with different priorities depending on whether they are located at the parking position, approach path, or other areas, and based on their azimuth and elevation angles relative to the vehicle's optical axis. This ensures that critical feature points contributing to position accuracy are registered while non-critical points are excluded.
Solution Approach 2:
The patent segments the space around the vehicle into multiple regions (parking position, approach path, other areas) and applies different feature point registration strategies to each segment. This segmentation allows the system to optimize feature point selection for each specific functional area rather than using a uniform approach across the entire map.
2Productivity
If the number of feature points registered on the map is reduced to decrease calculation amount, then processing efficiency improves, but position accuracy deteriorates due to insufficient feature points for reliable estimation
Solution Approach 1:
The patent ensures that feature points critical for position accuracy (those at favorable angles and locations) are prioritized for registration, while non-critical feature points are excluded. This selective registration based on local quality criteria maintains position estimation accuracy with a reduced overall number of feature points, thereby improving calculation efficiency.
3Ease of operation
If feature points are selected without considering their angle with respect to the optical axis, then the selection process is simple, but position accuracy deteriorates because feature points at unfavorable angles do not contribute effectively to position estimation
Solution Approach 1:
The patent introduces angular parameters (azimuth and elevation angles) as selection criteria for feature points. By evaluating feature points based on their angular relationship to the vehicle's optical axis, the system automatically filters out feature points at unfavorable angles that would not contribute effectively to position estimation, thereby improving accuracy while maintaining selection simplicity through automated parameter-based filtering.
4Device complexity
If the same feature point registration criteria are applied to all directions, then the system is easy to implement, but position accuracy deteriorates because the necessity of accuracy differs between front-rear and left-right directions
Solution Approach 1:
The patent applies different feature point registration criteria to different spatial directions based on the specific accuracy requirements of each direction. For example, feature points in the front-rear direction may be selected with different angular thresholds and priority levels compared to feature points in the left-right direction. This direction-specific approach ensures that each directional requirement is optimally satisfied while maintaining manageable system complexity through structured, direction-aware selection rules.
Data Source
AI summary
A parking assistance apparatus includes: an image acquirer that acquires a camera image; a feature point detector that extracts feature points from the camera image; a feature point selector that selects a feature point to be registered on a map by evaluating the feature points in learning travel and a parking route and a parking position of the vehicle are registered on the map; and a vehicle controller that parks the vehicle based on the map, in which the feature point selector varies a priority for registration of the feature points or the number of feature points for registration in accordance with a position on the parking route, or selects, at the position on the parking route, the feature point to be registered on the map, based on a position of the camera or a relative position of the feature point with respect to an optical axis direction.