Aircraft inspection based on improved Swin Transformer

Li Feng; Jia Jun

doi:10.1117/12.3025486

28 February 2024 Aircraft inspection based on improved Swin Transformer

Li Feng, Jia Jun

Proceedings Volume 13071, International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023); 130710N (2024) https://doi.org/10.1117/12.3025486
Event: International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023), 2023, Shenyang, China

Abstract

With the rapid development of deep learning in the field of image processing, aircraft detection technology has become a hot spot in computer vision research. In this context, this paper proposes an airplane detection model based on improved Swin-Transformer. The model mainly integrates two advanced techniques: the attention mechanism of ECA (Efficient Channel Attention) and the multi-scale module of BiFPN (Bidirectional Feature Pyramid Network).The introduction of the ECA attention mechanism enables the model to more accurately capture and emphasize the aircraft features of key channel information, thus enhancing the recognition of aircraft targets. Meanwhile, the application of BiFPN optimizes the model's performance in dealing with aircraft targets at different scales, which is especially more effective in detecting small or long-range aircraft. A series of experiments on standard aircraft detection datasets show that our improved model achieves 98.3% and 97.6% in terms of accuracy and recall, respectively, compared to the traditional Swin-Transformer model. These results not only demonstrate the value of the ECA attention mechanism and BiFPN in aircraft detection, but also provide a new direction for future Transformer-based target detection research.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Li Feng and Jia Jun "Aircraft inspection based on improved Swin Transformer", Proc. SPIE 13071, International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023), 130710N (28 February 2024); https://doi.org/10.1117/12.3025486

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Target detection

Performance modeling

Object detection

Feature fusion

Visual process modeling

Data modeling

Transformers

Show All Keywords

Keywords/Phrases

Search In:

Publication Years