Host Vehicle Position Estimation Using Intermediate Object Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional host vehicle position estimation devices struggle to accurately estimate the position of a host vehicle on a map when no referable landmark is present in the image photographed by the camera, leading to instability in the device.
Innovation Solution
The device estimates the host vehicle position using intermediate information from an intermediate object extracted from the image, such as a guide sign or display board, along with distance information and pre-stored landmark data, allowing for accurate positioning even without recognizable landmarks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the device relies on traditional landmark recognition for position estimation, then it can achieve accurate positioning when landmarks are present, but it fails to estimate position and loses stability when no referable landmark is present in the image
Solution Approach 1:
The patent introduces an intermediate object (such as a guide sign or display board) as a mediator between the camera and the final landmark. This intermediate object contains information about the landmark's name and distance, allowing the system to estimate position even when the landmark itself is not directly visible in the image. The intermediate object acts as a bridge that provides indirect information about the landmark's location and characteristics.
Solution Approach 2:
The system performs preliminary extraction of intermediate information from guide signs or display boards before attempting to recognize landmarks. By pre-extracting information such as landmark names and distances from these intermediate objects, the system prepares data that can be used for position estimation even when the actual landmarks are not visible, thus maintaining reliability under varying conditions.
2Measurement precision
If the device uses only recognizable landmarks for position estimation, then it maintains simple processing logic, but it cannot accurately estimate position in environments where landmarks are absent or unrecognizable
Solution Approach 1:
The patent makes the position estimation system universal by enabling it to work with multiple types of information sources. It can process both traditional landmark recognition and intermediate object information extraction, allowing the same system to function accurately in diverse environments whether landmarks are directly visible or only indirectly referenced through guide signs and display boards.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a host vehicle position estimation device capable of accurately estimating the position of a host vehicle on a map even if there is no landmark that can be referred to on an image photographed using a camera. A host vehicle position is estimated on the basis of intermediate information about a landmark name and landmark distance for an intermediate object extracted from a photographed image of the surroundings of a host vehicle, distance information about the distance to the intermediate object, and landmark information stored beforehand about the landmark name and position.