Vehicle Position Estimation Using Universal and Unique Feature Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for estimating the position of a vehicle from camera-captured images lack sufficient accuracy for applications like auto valet parking and autonomous driving.
Innovation Solution
A vehicle position estimation system that uses a trained model to extract universal and unique feature points from images, where universal feature points are independent of vehicle type and unique feature points are specific to each type, allowing for precise position estimation based on image coordinates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional feature point extraction methods are used, then the system structure is simple, but the position estimation accuracy is insufficient
Solution Approach 1:
The feature point extraction system is segmented into multiple specialized layers: a universal feature point extraction layer that works for all vehicle types, and multiple vehicle-type-specific unique feature point extraction layers. This segmentation allows each layer to be optimized for its specific function, improving overall position estimation accuracy while maintaining manageable system complexity through modular architecture.
Solution Approach 2:
Different feature point extraction layers are designed with different qualities and characteristics tailored to their specific purposes. The universal layer provides general-purpose feature extraction, while each unique layer provides specialized extraction optimized for its specific vehicle type. This local quality approach enables high-precision position estimation by using the most appropriate extraction method for each feature point type.
2Measurement precision
If vehicle-type-specific unique feature points are added, then position estimation accuracy improves, but the model complexity increases
Solution Approach 1:
The model is segmented into a shared universal feature point extraction layer and separate vehicle-type-specific unique feature point extraction layers. This segmentation allows the system to capture both universal features common to all vehicles and unique features specific to each vehicle type, improving position estimation accuracy while managing complexity through a hierarchical modular structure.
Solution Approach 2:
The universal feature point extraction layer serves multiple functions by extracting feature points that are common across all vehicle types. This multi-functional layer reduces the overall model complexity by sharing common processing logic while still allowing vehicle-type-specific layers to add specialized capabilities when needed.
Data Source
AI summary
A vehicle position estimation system comprises one or more processors configured to estimate a position of a target vehicle shown in an image captured by a camera. The vehicle position estimation system extracts a universal feature point and a plurality of types of unique feature points from the captured image using a trained model. The universal feature point is a feature point independent of vehicle type. Each of the plurality of types of unique feature points is a feature point corresponding to each of a plurality of applicable vehicle types. The vehicle position estimation system selects a target unique feature point from the plurality of types of unique feature points according to the vehicle type of the target vehicle. Then, the vehicle position estimation system estimates the position of the target vehicle based on image coordinates of the universal feature point and the target unique feature point.