Position Estimation Using Vehicle-Type-Specific Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of position estimation for moving objects, such as vehicles, decreases due to differences in vehicle class and characteristics when using captured images from outside, affecting various types of vehicles and moving objects.
Innovation Solution
A position estimation device that acquires images, identifies the type of moving object, and transforms local coordinates into global coordinates using specific parameters, accounting for the type of object to improve estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If position estimation is performed using captured images from outside the vehicle, then the position can be estimated without additional sensors on the vehicle, but the accuracy decreases due to differences in vehicle class and characteristics
Solution Approach 1:
The patent applies local quality by using vehicle-specific parameters (such as vehicle length, width, height, and positioning point location) that are tailored to each vehicle type. These localized parameters are used to transform coordinates from the image coordinate system to the vehicle coordinate system, thereby improving position estimation accuracy for each specific vehicle class while maintaining the overall system's ease of implementation.
Solution Approach 2:
The patent employs parameter changes by introducing vehicle-specific parameters (length, width, height, positioning point coordinates) that vary according to vehicle type. By changing these parameters based on the identified vehicle class, the system adapts the position estimation process to accommodate different vehicle characteristics, thus resolving the accuracy issue without requiring different hardware for each vehicle type.
2Device complexity
If a single position estimation method is used for all vehicle types, then the system remains simple and unified, but accuracy decreases due to variations in vehicle class characteristics
Solution Approach 1:
The patent achieves universality by creating a unified position estimation system that can handle multiple vehicle types through a common framework. The system uses a general coordinate transformation method that incorporates vehicle-specific parameters, allowing it to adapt to different vehicle classes (passenger cars, trucks, buses, etc.) without requiring separate estimation algorithms for each type. This maintains system simplicity while improving accuracy across diverse vehicle types.
Solution Approach 2:
The patent applies dynamics by making the position estimation system adaptive to different vehicle types through dynamic parameter selection. The system identifies the vehicle type first, then dynamically selects or adjusts the appropriate vehicle parameters (length, width, height, positioning point location) for that specific type. This dynamic adaptation allows a single unified system to achieve high accuracy across varying vehicle characteristics.
Data Source
AI summary
A position estimation device that estimates a position of a moving object includes: an acquisition unit that acquires a captured image including the moving object from an imaging device; a position calculation unit that calculates a local coordinate point that indicates the position of the moving object in a local coordinate system using the captured image; a type identification unit that identifies a type of the moving object included in the captured image; and a position transformation unit that transforms the local coordinate point into a moving object coordinate point that indicates the position of the moving object in a global coordinate system using an imaging parameter calculated based on the position of the imaging device in the global coordinate system and a moving object parameter determined according to the type of the moving object.