Camera-Based Position Estimation Without Vehicle Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing position estimation systems require installation objects on vehicles, making it impossible to estimate positions when such objects cannot be installed.
Innovation Solution
A position estimation system that uses a camera to photograph a moving body, applies image processing techniques like perspective transformation and mask generation to calculate the body's position without requiring installation objects on the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If installation objects are used on vehicles and parking spaces for position detection, then position detection accuracy is improved, but the system cannot be applied to moving bodies without installation objects
Solution Approach 1:
The patent uses a bird's-eye view image as a virtual copy of the actual parking space layout to enable position estimation without physical installation objects. The bird's-eye view image contains coordinate information that corresponds to real-world positions, allowing the system to calculate vehicle positions by matching detected vehicle images with their corresponding positions in the bird's-eye view image
Solution Approach 2:
The patent replaces the mechanical installation-based detection system with an image processing-based system. Instead of using physical installation objects on vehicles and in parking spaces, the system uses imaging units to capture images and processes these images through perspective transformation and coordinate mapping to achieve position estimation
2Ease of operation
If installation objects are installed on vehicles and in parking spaces, then position estimation can be achieved, but the system complexity and installation requirements increase
Solution Approach 1:
The patent extracts the essential position information from the complex installation system by using only bird's-eye view images and vehicle images. The system removes the need for installation objects on vehicles and in parking spaces, keeping only the imaging units and image processing components
Solution Approach 2:
The imaging units serve multiple functions: they capture both the bird's-eye view image of the parking space and the images of vehicles for position estimation. The same imaging hardware is used for both mapping and detection purposes, reducing the need for separate installation objects
Data Source
AI summary
A position estimation system, a position estimation method, and a program that can estimate a position of a moving body without installing an installation object on the moving body are provided. A position estimation system includes a detection unit configured to generate a first mask image, a mask area masking a moving body in an image photographed being added to the first mask image, a perspective transformation unit configured to perform perspective transformation on the first mask image, and a position calculation unit configured to correct a coordinate point of a first circumscribed rectangle set for a mask area in the first mask image using a second coordinate point of the mask area in the second mask image, which is obtained by performing perspective transformation on the first mask, to calculate a third coordinate point.