Refueling Boom Tip 3D Positioning From a Single Camera
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately and efficiently conducting aerial refueling operations using cameras is difficult with current techniques.
Innovation Solution
A system and method utilizing a single camera to receive a 2D image, determine 2D keypoints of a refueling boom, estimate a 6 degree-of-freedom (6DOF) pose, and calculate the position of the boom tip using 3D keypoints, incorporating a processor and non-transitory computer readable storage media to execute these operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current camera-based techniques are used for aerial refueling, then the refueling operation can be conducted, but the accuracy and efficiency are difficult to achieve
Solution Approach 1:
The patent replaces complex mechanical measurement systems with a computational vision system. Instead of using multiple cameras, lasers, or mechanical sensors to directly measure boom position, the system uses a single camera to capture images and then applies computer vision algorithms (keypoint detection, 6DOF pose estimation, ray casting) to computationally determine the boom tip position. This substitution of mechanical measurement with computational methods achieves high measurement precision while reducing device complexity.
Solution Approach 2:
The patent introduces an intermediary computational processing layer between the camera and the final position determination. The intermediary steps include detecting 2D keypoints in the image, estimating 6DOF pose parameters, and calculating the 3D boom tip position through ray casting. This intermediary computational mediation allows the system to extract precise position information from simple 2D camera images, achieving accuracy without requiring complex direct measurement hardware.
2Measurement precision
If multiple sensors and complex systems are used to track boom position, then measurement accuracy improves, but the system complexity and difficulty of operation increase
Solution Approach 1:
The system enables the camera to essentially track and measure the boom position autonomously through its own computational processing. The computer vision algorithm automatically detects keypoints, estimates pose, and calculates position without requiring external measurement systems or complex manual intervention. This self-service capability simplifies operation while maintaining high measurement precision.
Solution Approach 2:
By replacing complex mechanical sensor arrays with a single camera and computational vision system, the patent reduces the operational complexity of the refueling system. The computational methods automatically handle the complex calculations that would otherwise require complex mechanical systems, making the overall system easier to operate while maintaining or improving measurement precision.
Data Source
AI summary
Disclosed herein is methods, systems, and aircraft for performing image analysis for aiding refueling operations. A tanker aircraft includes a single camera, a refueling boom, a camera configured to generate a 2D image of the refueling boom, a processor, and non-transitory computer readable storage media storing code. The code being executable by the processor to perform operations comprising receiving the 2D image from the single camera, determining 2D keypoints of the refueling boom located within the 2D image based on a predefined point model of the refueling boom, determining keypoints in 3D space based on the 2D keypoints to produce 3D keypoints, determining a 6DOF pose using the 2D keypoints and the 3D keypoints, and estimating a position of a tip of the refueling boom based on the 6DOF pose.