Object Detection Device Disparity Map Coordinate Update
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection devices using stereo cameras face challenges in accurately detecting objects on a road surface, particularly in scenarios where the disparity map contains multiple pairs of coordinates with disparities close to the target disparity, leading to incorrect updates and reduced detection performance.
Innovation Solution
The object detection device employs a processor to search for pairs of coordinates in a disparity map with a disparity approximately equal to a target disparity, updating the coordinates accordingly and calculating the height of objects based on these coordinates. It also considers a predetermined interval and the presence of pairs with smaller disparities to refine the coordinate updates and ensure accurate object height calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the processor updates coordinates in the disparity map based on closest disparity matching, then the object height calculation becomes simpler, but the detection accuracy deteriorates due to incorrect coordinate updates when multiple coordinate pairs have similar disparities
Solution Approach 1:
The processor performs feedback verification by checking whether coordinate updates produce consistent disparity values. After updating coordinates to find the closest disparity match, the system verifies whether the updated coordinates yield the expected target disparity. If verification fails (indicating incorrect update due to multiple similar disparities), the system maintains the original coordinates, thus preventing accuracy degradation while preserving computational efficiency.
2Speed
If the processor searches for the closest disparity in the disparity map, then the processing speed increases, but the reliability of object detection decreases due to incorrect coordinate updates
Solution Approach 1:
The system performs preliminary verification before finalizing coordinate updates. When searching for the closest disparity, the processor first identifies candidate coordinate pairs, then pre-verifies whether updating to these candidates would produce valid results by checking disparity consistency. This preliminary check prevents unreliable updates while maintaining fast processing by avoiding exhaustive verification of all possible coordinate pairs.
Data Source
AI summary
A processor of an object detection device is configured to search for a pair of coordinates associated with a disparity approximately equal to a target disparity satisfying a predetermined condition in a second direction of a disparity map, update a first pair of coordinates to the found pair of coordinates, and calculate a height of an object corresponding to the target disparity on the basis of the first pair of coordinates. In the disparity map, a disparity acquired from a captured image is associated with a pair of two-dimensional coordinates formed by a first direction and the second direction intersecting the first direction. When a second pair of coordinates associated with a disparity approximately equal to the target disparity is present within a predetermined interval from the first pair of coordinates, the processor is configured to update the first pair of coordinates to the second pair of coordinates.