Aruco Marker Extraction for GNSS-Denied Aircraft Landing Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
UAS navigation systems face challenges in landing at vertiports without GNSS, requiring robust sensor alternatives to ensure accurate navigation in both GNSS-available and GNSS-denied environments, especially for unpowered or minimally powered vertiports.
Innovation Solution
A method for extracting Aruco codes from vehicle camera images using multiple techniques and window sizes to enhance the robustness of marker detection, involving multi-scale-binarization, adaptive thresholding, and contour verification to ensure accurate identification of landing surface markers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional GNSS-based navigation is used, then navigation accuracy is maintained in open environments, but the system fails completely in GNSS-denied environments such as vertiports without powered infrastructure
Solution Approach 1:
The navigation system is segmented into multiple independent components: GNSS-based navigation for open environments and vision-based Aruco code detection for GNSS-denied environments. This segmentation allows each component to specialize in specific conditions, with the vision-based system activated only when GNSS is unavailable, thus maintaining reliability across diverse environments without requiring the vision system to operate continuously.
Solution Approach 2:
A sensor fusion architecture acts as an intermediary between GNSS and vision-based navigation systems. This intermediary layer integrates data from both systems and automatically switches between them based on environmental conditions, ensuring seamless transition and maintaining navigation reliability whether the UAS operates in GNSS-available or GNSS-denied environments.
2Measurement precision
If multiple processing techniques and window sizes are used for Aruco code detection, then detection accuracy and robustness are improved, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary actions by converting the color image to grayscale and applying Gaussian blur before edge detection. These preprocessing steps simplify the image data and reduce noise, making subsequent multi-scale edge detection more efficient and accurate while reducing the computational burden of processing the original color image at multiple scales.
Solution Approach 2:
The system applies multiple edge detection techniques (Canny, Sobel, Prewitt) and multiple window sizes, which represents an excessive approach to ensure comprehensive detection. However, this is justified in vertiport landing scenarios where high detection accuracy is critical for safety, and the system can filter false positives through multiple validation steps including contour analysis and bit pattern verification.
3Ease of manufacture
If unpowered surface features like Aruco codes are used instead of powered navigation infrastructure, then infrastructure requirements are reduced, but detection reliability may be affected by environmental factors such as lighting and image quality
Solution Approach 1:
The system changes parameters by detecting Aruco codes at multiple scale levels and adjusting window sizes dynamically. This allows the detection algorithm to adapt to varying distances and lighting conditions, maintaining reliability across different environmental scenarios while using simple unpowered surface features.
Solution Approach 2:
The system implements feedback through iterative refinement of contour detection and validation. Detected contours are validated against expected Aruco code characteristics (four-sided polygons, specific bit patterns), and detection results feed back into adjusting processing parameters for subsequent detections, thereby maintaining high reliability despite environmental variations.
Data Source
AI summary
A method comprises capturing, with a vehicle vision sensor, a color image of a landing site including landing surface markers; converting the color image to a gray scale image; and performing multi-scale-binarization to detect multiple edges of the gray scale image and produce binary images. The method determines contours of edges of the binary images having closed shapes, detects closed shapes of contours of edges having four corners, and verifies whether four-sided candidate contours are valid as potential landing surface markers. If more than one contour is associated with a valid ID within a surface marker library, then the contour within the smallest window size is selected. If multiple contours with the same window size can be associated with a valid ID, then a mean of corresponding corners of multiple contours is computed. The method then performs corner refinement of valid four-sided candidate contours identified as potential landing surface markers.