Adaptive Gaussian Derivative Sigma for Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inertial Navigation Systems (INS) using Inertial Measurement Units (IMU) suffer from accumulated errors, which can lead to significant navigation parameter discrepancies over time, and these errors cannot be effectively corrected when Global Navigation Satellite Systems (GPS) are unavailable due to outages or interference.
Innovation Solution
A method that normalizes remote sensing images to match the dimensions and spatial resolutions of onboard camera images, allowing for the generation and comparison of edge maps to correct navigation data, using techniques such as Canny edge detection and spatial resolution alignment, enabling precise vehicle positioning even without GPS.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS is used to correct navigation parameters, then navigation accuracy is improved, but system reliability deteriorates when GPS is unavailable due to outages or interference
Solution Approach 1:
The patent introduces remote sensing images as an intermediary medium to correct navigation parameters. Instead of directly using GPS signals, the system uses images captured by remote sensing devices (such as cameras or sensors on satellites or aircraft) as a mediator to determine vehicle position and correct navigation data, thereby maintaining system reliability when GPS is unavailable
Solution Approach 2:
The patent creates a copy of the navigation correction function by using remote sensing images to replicate the position determination capability that would otherwise require GPS. The system captures images, processes them to identify vehicle position, and uses this positional information to correct navigation parameters, effectively copying GPS functionality without relying on GPS signals
2Reliability
If remote sensing images are used for navigation correction, then system reliability is improved when GPS is unavailable, but measurement precision deteriorates due to differences in spatial resolution and image dimensions
Solution Approach 1:
The patent applies parameter changes by transforming the remote sensing images to match the expected spatial resolution and dimensions. The system adjusts image parameters such as resolution, size, and formatting to align with the vehicle's navigation system requirements, ensuring that the positional data extracted from the images can be accurately integrated with the navigation correction algorithm
3Measurement precision
If image processing is performed to match spatial resolutions, then measurement precision is improved for edge detection, but device complexity increases due to additional processing steps
Solution Approach 1:
The patent applies preliminary action by pre-processing the remote sensing images to match the expected spatial resolution and dimensions before the actual edge detection and navigation correction processes. The system performs dimensionality transformation and resolution adjustment in advance, so that when the images are used for navigation correction, the processing steps are already optimized, reducing overall system complexity
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In one embodiment, a method is provided. The method comprises determining a first value of a coefficient of an edge-determining algorithm in response to a spatial resolution of a first image acquired with an image capture device onboard a vehicle, a spatial resolution of a second image, and a second value of the coefficient in response to which the edge-determining algorithm generated a second edge map corresponding to the second image. The method further comprises determining, with the edge-determining algorithm in response to the coefficient having the first value, at least one edge of at least one object in the first image. The method further comprises generating, in response to the determined at least one edge, a first edge map corresponding to the first image. The method further comprises determining at least one navigation parameter of the vehicle in response to the first and second edge maps.