Research on infrared image target extraction method based on constrained Otsu method

Tianyu Wu; Zhong Lv; Tan Yong

doi:10.1117/12.2690040

6 November 2023 Research on infrared image target extraction method based on constrained Otsu method

Tianyu Wu, Zhong Lv, Tan Yong

Proceedings Volume 12921, Third International Computing Imaging Conference (CITA 2023); 1292129 (2023) https://doi.org/10.1117/12.2690040
Event: Third International Computing Imaging Conference (CITA 2023), 2023, Sydney, Australia

Abstract

Infrared images have advantages such as strong anti-interference ability and working day and night, and have been widely used in important places monitoring, traffic management, and other fields. However, infrared images also have problems such as poor contrast and low signal-to-noise ratio, which result in the feature extraction of targets in infrared images not being visible and bright and cannot meet the needs of target recognition in complex backgrounds. Based on this, a fusion method combining interactive strokes-based Otsu method with morphological operations is proposed. This method is based on the principle of maximum inter class variance, maximum flow/minimum cut, and digital morphology to establish an image object extraction model, which takes into account the accuracy and noise resistance of image extraction.

Citation Download Citation

Tianyu Wu, Zhong Lv, and Tan Yong "Research on infrared image target extraction method based on constrained Otsu method", Proc. SPIE 12921, Third International Computing Imaging Conference (CITA 2023), 1292129 (6 November 2023); https://doi.org/10.1117/12.2690040

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