Map Generation with Stable 3D Feature-Point Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map generation systems struggle with maintaining accurate environmental maps due to changes in landscape features over time, leading to incorrect vehicle position estimation.
Innovation Solution
A map generation apparatus that prioritizes selecting feature points based on their susceptibility to environmental changes, using a priority system to select stable objects like roads and traffic signs for three-dimensional position calculation, and updates the map by evaluating and deleting irrelevant features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If all extracted feature points are used for map generation, then the map contains comprehensive environmental information, but the map accuracy deteriorates due to inclusion of transient objects that change over time
Solution Approach 1:
The patent applies local quality by assigning different priorities to different feature points based on their object types. Stable objects like roads and buildings are assigned high priority and retained in the map, while transient objects like vehicles and pedestrians are assigned low priority and excluded. This selective retention based on local characteristics resolves the contradiction by maintaining map accuracy through differential treatment of feature points.
Solution Approach 2:
Instead of including all feature points and filtering out unwanted ones, the patent inverts the approach by selectively including only high-priority feature points from the beginning. The selection process prioritizes stable environmental features and excludes transient objects, achieving accurate maps without incorporating problematic feature points.
2Adaptability or versatility
If feature points on transient objects are included in the map, then the map reflects current environmental details, but the map becomes outdated quickly as these features change or disappear
Solution Approach 1:
The patent differentiates between stable and transient feature points by assigning priority levels. High-priority feature points from stable objects (roads, buildings) are retained long-term, while low-priority feature points from transient objects (vehicles, pedestrians) are excluded. This resolves the contradiction by maintaining map validity through selective inclusion of only those features that persist over time.
3Quantity of substance
If a large number of feature points are processed for three-dimensional position calculation, then the map provides detailed environmental representation, but the computational load and processing time increase
Solution Approach 1:
The patent extracts and selects only the necessary high-priority feature points from the complete set of extracted feature points. By filtering out low-priority transient objects before three-dimensional position calculation, the system reduces the number of points requiring computationally intensive processing while maintaining the essential environmental representation needed for accurate mapping.
Solution Approach 2:
Instead of processing all extracted feature points equally, the patent applies partial action by focusing computational resources only on high-priority feature points. This selective processing achieves sufficient map detail for vehicle positioning without the excessive computational burden of processing every single feature point.
Data Source
AI summary
A map generation apparatus includes a microprocessor configured to perform: extracting feature points from detection information detected by an in-vehicle detection unit; selecting feature points for which three-dimensional positions are to be calculated from extracted feature points; based on a plurality of the detection information, calculating the three-dimensional positions of same feature points in the plurality of the detection information for the selected feature points by using a position and posture of the in-vehicle detection unit; and generating a map including information of each of the three-dimensional positions by using the three-dimensional positions of the calculated feature points, wherein the microprocessor is configured to perform the selecting including selecting the feature points on an object with a high priority among a plurality of objects included in the detection information based on a priority information set for each of the plurality of objects in advance.