Identification and location technology of refueling taper sleeve based on deep learning

Guoxing Hu; Haoguang Liu

doi:10.1117/12.3007578

18 December 2023 Identification and location technology of refueling taper sleeve based on deep learning

Guoxing Hu, Haoguang Liu

Proceedings Volume 12968, AOPC 2023: Optic Fiber Gyro ; 129681K (2023) https://doi.org/10.1117/12.3007578
Event: Applied Optics and Photonics China 2023 (AOPC2023), 2023, Beijing, China

Abstract

In the process of aerial refueling test flight and autonomous aerial refueling, it is necessary to measure the high-precision motion parameters of the Taper sleeve relative to the oil-receiving probe to provide data for the docking process. In this paper, aiming at the problems of intelligent identification and tracking of aerial refueling targets and high-precision stereo vision positioning, a multi-layer convolutional neural network with visual characteristics was constructed by deep learning theory, and the recognition results of Taper sleeve were corrected by using frame regression algorithm, so as to improve the Taper sleeve positioning accuracy from three dimensions: identification and tracking, optical calibration and measurement and solution. In this paper, combined with the test and flight verification, the solution accuracy is better than 0.09%, the identification success rate is better than 98%, and the Taper sleeve positioning accuracy is better than2cm+0.15%*L, which accords with the positioning accuracy of the refueling taper sleeve in the flight test.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Guoxing Hu and Haoguang Liu "Identification and location technology of refueling taper sleeve based on deep learning", Proc. SPIE 12968, AOPC 2023: Optic Fiber Gyro , 129681K (18 December 2023); https://doi.org/10.1117/12.3007578

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available