Intersecting Road Edge Estimation via Stationary Object Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques fail to accurately estimate the road edge of an intersecting road by mixing stationary objects from the traveling road with those from the intersecting road, leading to misrecognition and inaccurate detection of moving objects.
Innovation Solution
A vehicle-mounted intersecting road estimation device using a millimeter-wave radar, camera, and microcomputer to detect objects, extract stationary objects, and differentiate between road edges of the traveling and intersecting roads, employing a candidate extraction and second estimation unit to accurately estimate the road edge of the intersecting road.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If stationary objects from both traveling road and intersecting road are mixed in detection results, then the detection process is simplified, but the measurement precision of road edge position deteriorates
Solution Approach 1:
The patent segments the detection process into distinct stages: first detecting all stationary objects, then separating them into two groups based on their positional relationships with the traveling road. The object extraction unit divides stationary objects into those representing the traveling road edge and those representing the intersecting road edge, allowing precise measurement of both road edges without confusion.
Solution Approach 2:
The patent extracts and isolates stationary objects that represent the intersecting road edge from the mixed detection results. By identifying and separating these objects based on their position relative to the traveling road edge, the system can accurately measure the intersecting road edge position without interference from traveling road objects.
2Device complexity
If stationary objects are used to estimate road edges, then the measurement process is simplified, but the reliability of moving object detection deteriorates due to misrecognition
Solution Approach 1:
The patent segments stationary objects into distinct functional groups: objects representing the traveling road edge and objects representing the intersecting road edge. This segmentation allows the system to use stationary objects for road edge estimation while preventing misrecognition that would compromise moving object detection reliability.
Solution Approach 2:
The patent introduces an intermediary classification process that acts as a mediator between raw detection results and final road edge estimation. The object extraction unit serves as this intermediary, filtering and categorizing stationary objects to produce accurate road edge positions without introducing errors that would affect moving object detection.
Data Source
AI summary
An intersecting road estimation device includes an object detection unit that detects an object existing around an own vehicle and a position of the object, an object extraction unit that extracts a stationary object and a position of the stationary object from an object detection result, a first estimation unit that estimates a road edge of a traveling road on which the own vehicle is traveling based on the position of the stationary object, a candidate extraction unit that extracts a stationary object existing outside the road edge of the traveling road estimated by the first estimation unit as a candidate for an outside stationary object representing a road edge of an intersecting road intersecting the traveling road, and a second estimation unit that estimates the road edge of the intersecting road based on a position of the outside stationary object extracted by the candidate extraction unit.