红外技术2016，Vol.38Issue(3)：230-235,6.
基于核稀疏编码的红外目标识别方法
An Infrared Target Recognition Method Based on Kernel Sparse Coding
杨春伟 1王仕成 2廖守亿 1刘华平1
作者信息
- 1. 第二炮兵工程大学精确制导仿真技术实验室,陕西西安 710025
- 2. 清华大学计算机科学与技术系,北京 100084
- 折叠
摘要
Abstract
An infrared target recognition method based on covariance descriptor and kernel sparse coding is proposed in this paper. Covariance descriptor combining infrared image gray intensity values and the norm of first and second order derivatives of the intensities as infrared image features. With respect tox andy is extracted as feature representation, similarity of covariance descriptors is computed through Log-Euclidean metric. Then covariance descriptors are mapped into a high dimensional feature space through Gaussian kernel function. Finally, infrared target recognition is accomplished using sparse coding in the new feature space. Experiments on the real infrared images show that our method obtains better results compared with traditional algorithms such as KNN and SVM.关键词
协方差描述子/核稀疏编码/红外目标识别Key words
covariance descriptor/kernel sparse coding/infrared target recognition分类
信息技术与安全科学引用本文复制引用
杨春伟,王仕成,廖守亿,刘华平..基于核稀疏编码的红外目标识别方法[J].红外技术,2016,38(3):230-235,6.
