Infrared image background modeling based on improved Susan filtering

Xia Yuehua

doi:10.1117/12.2305920

20 February 2018 Infrared image background modeling based on improved Susan filtering

Xia Yuehua

Proceedings Volume 10697, Fourth Seminar on Novel Optoelectronic Detection Technology and Application; 1069708 (2018) https://doi.org/10.1117/12.2305920
Event: Fourth Seminar on Novel Optoelectronic Detection Technology and Application, 2017, Nanjing, China

Abstract

When SUSAN filter is used to model the infrared image, the Gaussian filter lacks the ability of direction filtering. After filtering, the edge information of the image cannot be preserved well, so that there are a lot of edge singular points in the difference graph, increase the difficulties of target detection. To solve the above problems, the anisotropy algorithm is introduced in this paper, and the anisotropic Gauss filter is used instead of the Gauss filter in the SUSAN filter operator. Firstly, using anisotropic gradient operator to calculate a point of image's horizontal and vertical gradient, to determine the long axis direction of the filter; Secondly, use the local area of the point and the neighborhood smoothness to calculate the filter length and short axis variance; And then calculate the first-order norm of the difference between the local area of the point's gray-scale and mean, to determine the threshold of the SUSAN filter; Finally, the built SUSAN filter is used to convolution the image to obtain the background image, at the same time, the difference between the background image and the original image is obtained. The experimental results show that the background modeling effect of infrared image is evaluated by Mean Squared Error (MSE), Structural Similarity (SSIM) and local Signal-to-noise Ratio Gain (GSNR). Compared with the traditional filtering algorithm, the improved SUSAN filter has achieved better background modeling effect, which can effectively preserve the edge information in the image, and the dim small target is effectively enhanced in the difference graph, which greatly reduces the false alarm rate of the image.

Citation Download Citation

Xia Yuehua "Infrared image background modeling based on improved Susan filtering", Proc. SPIE 10697, Fourth Seminar on Novel Optoelectronic Detection Technology and Application, 1069708 (20 February 2018); https://doi.org/10.1117/12.2305920

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

Image filtering

Gaussian filters

Anisotropic filtering

Infrared imaging

Infrared radiation

Image enhancement

Anisotropy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years