Kernel sparse coding method for automatic target recognition in infrared imagery using covariance descriptor

•Covariance Descriptor is used as feature representation of infrared target.•A kernel sparse coding method for ATR in infrared imagery is proposed.•Experiments on the real infrared imagery show our method obtains good results. Automatic target recognition in infrared imagery is a challenging problem...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Infrared physics & technology Ročník 76; s. 740 - 747
Hlavní autoři: Yang, Chunwei, Yao, Junping, Sun, Dawei, Wang, Shicheng, Liu, Huaping
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.05.2016
Témata:
Automatic target recognition
Coding
Confusion
Covariance
Covariance descriptor
Effectiveness
Infrared
Infrared imagery
Kernel sparse coding
Kernels
Log-Euclidean metric
Automatic target recognition
Kernel sparse coding
Covariance descriptor
Log-Euclidean metric
ISSN:1350-4495, 1879-0275
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Covariance Descriptor is used as feature representation of infrared target.•A kernel sparse coding method for ATR in infrared imagery is proposed.•Experiments on the real infrared imagery show our method obtains good results. Automatic target recognition in infrared imagery is a challenging problem. In this paper, a kernel sparse coding method for infrared target recognition using covariance descriptor is proposed. First, covariance descriptor combining gray intensity and gradient information of the infrared target is extracted as a feature representation. Then, due to the reason that covariance descriptor lies in non-Euclidean manifold, kernel sparse coding theory is used to solve this problem. We verify the efficacy of the proposed algorithm in terms of the confusion matrices on the real images consisting of seven categories of infrared vehicle targets.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1350-4495
1879-0275
DOI:10.1016/j.infrared.2016.04.020