Road Surface Grid Mapping from Roadside Object Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing in-vehicle control systems face challenges in accurately determining the road surface region for vehicle travel due to the dispersion of occupied regions, leading to unclear boundary information and increased processing load.
Innovation Solution
An in-vehicle control device that includes an object detection unit, an object information storage unit, and an information processing unit to generate a determination grid map by replacing unoccupied regions with occupied regions, allowing for the identification of a closed space as a road surface region, thereby improving accuracy and reducing processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the occupied grid map is created by spreading the occupied region according to the degree of intensity from observed data, then the contrast between occupied and unoccupied regions is improved, but the clarity in position information of the detected object boundary is lowered
Solution Approach 1:
The patent divides the grid map processing into two distinct stages: first creating a pre-processing grid map with spread occupied regions for high contrast, then generating a determination grid map by selectively replacing unoccupied regions to restore boundary clarity. This segmentation allows each stage to optimize for its specific purpose without compromising the other.
Solution Approach 2:
The patent performs preliminary spreading of occupied regions in the pre-processing grid map to establish clear contrast between occupied and unoccupied areas. This preliminary action prepares the data structure for subsequent boundary clarification through selective replacement in the determination grid map stage.
2Ease of operation
If the occupied region is spread to clarify the contrast between occupied and unoccupied regions, then the region where the vehicle can travel becomes easier to identify, but the traveling region must be set in a narrow area avoiding uncertain regions
Solution Approach 1:
The patent segments the grid map processing into pre-processing and determination stages, allowing the pre-processing map to focus on contrast enhancement for easy identification, while the determination map restores boundary accuracy to maximize usable traveling area by eliminating unnecessary restrictions from uncertain regions.
Solution Approach 2:
The pre-processing grid map serves as a preliminary step that enhances contrast for easy identification of potential travel regions. The subsequent determination grid map then refines this by replacing unoccupied regions with occupied regions at boundaries, converting previously uncertain areas into usable travel space.
3Reliability
If the boundary of the region where the vehicle can travel is determined based on spread occupied regions, then the contrast is improved, but the determination accuracy of the road surface region is reduced
Solution Approach 1:
The patent divides the processing into two maps: the pre-processing grid map provides high contrast for reliable identification of occupied versus unoccupied regions, while the determination grid map restores measurement precision by selectively replacing unoccupied regions with occupied regions to accurately define road surface boundaries.
Solution Approach 2:
The pre-processing grid map performs the preliminary function of establishing clear contrast between occupied and unoccupied regions. The determination grid map then performs the refinement function of restoring boundary accuracy by replacing unoccupied regions with occupied regions, ensuring both contrast and precision are achieved in their respective stages.
Data Source
AI summary
A method determines the region where a vehicle can travel without changing clarity of the position information of the object detected by a sensor. An in-vehicle control device includes an object detection unit detecting the position of an object from image information captured by an image pickup device, an object information storage unit stores a pre-processing grid map including a position of a detected object set as an object occupied region and a position where no object has been detected is as an object unoccupied region, an information processing unit generates a determination grid map in which part of the object unoccupied region of the map is replaced with the object occupied region, and a road surface region determination unit that generates an automatic driving grid map in which a closed space surrounded by the object occupied region of the determination grid map is set as a road surface region.