Occupancy Grid Boundary Detection With ROI Transition Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for detecting free space around vehicles, such as in advanced driver assistance systems, require significant computational effort and are prone to errors in determining the boundary between free and occupied spaces.
Innovation Solution
A method and apparatus that utilize an occupancy grid to detect boundaries by identifying transition points and assigning region of interest windows, reducing computational effort by focusing analysis on specific areas and improving reliability through successive verification of detected boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire occupancy grid is analyzed to detect boundaries, then measurement precision is improved, but computation time increases
Solution Approach 1:
The occupancy grid is divided into multiple regions of interest (ROIs) based on detected transition points. Instead of analyzing the entire grid uniformly, the method segments the search space into specific ROIs surrounding transition points, where boundary detection is most critical. This segmentation allows concentrated computational resources on areas likely to contain boundaries while reducing overall computation time.
Solution Approach 2:
The method applies different analysis strategies to different regions of the occupancy grid. Regions containing transition points receive focused attention with detailed local analysis to detect boundaries with high precision, while other regions are either skipped or analyzed with less computational effort. This local quality approach ensures measurement precision at critical locations without uniformly increasing computation time across the entire grid.
2Reliability
If the entire occupancy grid is analyzed to detect boundaries, then reliability is improved, but computation effort increases
Solution Approach 1:
The method performs preliminary detection of transition points in the occupancy grid before conducting detailed boundary analysis. These transition points serve as indicators of potential boundary locations. By identifying and marking these points first, the system can then focus subsequent detailed analysis only on regions surrounding these transition points, ensuring reliable boundary detection without the computational effort required to analyze the entire grid in detail.
Solution Approach 2:
The occupancy grid analysis is segmented into two stages: first detecting transition points across the grid, then performing detailed boundary detection only in regions of interest surrounding these transition points. This segmentation allows the system to maintain high reliability by thoroughly analyzing critical regions while reducing overall computation effort by excluding non-critical regions from detailed analysis.
3Productivity
If region of interest windows are assigned around transition points, then productivity is improved, but device complexity increases
Solution Approach 1:
The regions of interest are dynamically defined based on the detected transition points rather than using fixed grid segments. The size, shape, and position of each ROI are adapted to the specific location and characteristics of the transition point it surrounds. This dynamic approach improves productivity by focusing computational resources precisely where needed, while the adaptability reduces the need for overly complex predetermined segmentation schemes.
Data Source
Figure 1~3
Figure 4~5
AI summary
The present invention provides to a detection of a boundary in an environment. For this purpose, information of an occupancy grid is used, wherein the occupancy grid provides information about the probability of occupancy in the environment. Upon detecting a starting transition point between a free and an occupied grid cell in the occupancy grid, a region of interest window surrounding the starting transition point is analyzed to identify further transition points. The identified transition points are combined to one or more polygon chain. After the analysis of the boundary is performed within the region of interest, successive regions of interest may be analyzed. For this purpose, the successive regions of interest are determined based on the transition points and/or the boundary information of a current region of interest window.