Target detection of hyperspectral imagery

Hang Qu; Lei Xiao; Xinghua Hou

doi:10.1117/12.2623067

27 March 2022 Target detection of hyperspectral imagery

Hang Qu, Lei Xiao, Xinghua Hou

Proceedings Volume 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications; 121692P (2022) https://doi.org/10.1117/12.2623067
Event: Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 2021, Kunming, China

Abstract

For target detection of hyperspectral imagery, this paper proposes a K - L transformation method based on spectral characteristics is introduced to extract the significant profile target. The significant characteristics represents the significant information, spatial distribution of the significant region and correlation information in the image. Profile features can reflect the correlation information of the background and target in the significant region from a whole. Target detection can be realized by classifying these regions. Since the method above could not accurately obtain targets like human visual ability and detect several regions in one target, a kind of an algorithm based on difference will be put forward in this paper. Firstly, the background for comparison must be selected according to the original image. Then, the object-of-interest could be obtained by comparing the difference between the image and the background template. Furthermore, multiple targets in the same region can be marked respectively by the difference method.

Citation Download Citation

Hang Qu, Lei Xiao, and Xinghua Hou "Target detection of hyperspectral imagery", Proc. SPIE 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 121692P (27 March 2022); https://doi.org/10.1117/12.2623067

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