Infrared dim and small target detection algorithm based on background perception

Dong Cao; Yang Zhao; Henghui Wang

doi:10.1117/12.2663448

4 April 2023 Infrared dim and small target detection algorithm based on background perception

Dong Cao, Yang Zhao, Henghui Wang

Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126170V (2023) https://doi.org/10.1117/12.2663448
Event: 9th Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China

Abstract

In order to improve the detection performance of infrared small targets in complex background, a target detection method based on background perception is proposed in this paper. The curvature filtering is introduced into background estimation algorithm, and a fast discrete filter based on Gaussian curvature regularizer is constructed. In the tangent plane of all the neighborhood pixels, we use the principle of minimum distance adjustment to modify the pixel value by finding the face closest to the current pixel. This method can better preserve image details and obtain the accurate background estimation. Experiments were carried out on open data sets, and experimental results show that the algorithm can better adapt to complex background environment. Compared with traditional methods, the algorithm has the advantages of high detection probability and lower false alarm rate for infrared dim and small targets.

Citation Download Citation

Dong Cao, Yang Zhao, and Henghui Wang "Infrared dim and small target detection algorithm based on background perception", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126170V (4 April 2023); https://doi.org/10.1117/12.2663448

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