Infrared dim and small target detection method based on three-layer four-direction and single-scale local contrast

Heng Yang; Qiang Zhang; Ruohan Feng

doi:10.1117/12.2620744

27 March 2022 Infrared dim and small target detection method based on three-layer four-direction and single-scale local contrast

Heng Yang, Qiang Zhang, Ruohan Feng

Author Affiliations +

Proceedings Volume 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications; 121690R (2022) https://doi.org/10.1117/12.2620744
Event: Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 2021, Kunming, China

Abstract

Aiming at the problem of complex clouds under the infrared background of the sky and the edges of buildings are likely to cause false alarms in the detection algorithm, an Three-layer four-direction and single-scale local contrast method is proposed. A three-layer window consisting of an inner layer, a middle layer, and an outer layer. The center layer window breaks the previous cognition of fixed-size windows, and uses multi-scale Gaussian filtering to enhance the target . The middle layer window is the isolation layer, its function is to isolate the target and the background area, and it has the ability to adapt to multiple scales of the target, and outer window is used for background extraction. This algorithm uses the idea of cascading magnification and the calculation method of diagonal gray difference, which can effectively enhance the target, suppress the background and background edges, and has good robustness to multi-scale target detection.

Citation Download Citation

Heng Yang, Qiang Zhang, and Ruohan Feng "Infrared dim and small target detection method based on three-layer four-direction and single-scale local contrast", Proc. SPIE 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 121690R (27 March 2022); https://doi.org/10.1117/12.2620744

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