检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]军械工程学院 [2]中国人民解放军73101部队
出 处:《光学仪器》2013年第5期27-31,共5页Optical Instruments
摘 要:现代战争中,高光谱成像技术开始应用于伪装目标识别.为了加强对高光谱图像的信息挖掘,确定可以用来进行伪装识别的目标高光谱特征,对高光谱成像条件下的迷彩伪装特性及影响伪装效果的因素进行了综合分析.在光谱维,从高光谱图像中直接提取光谱曲线,确定了图像对比度高、迷彩伪装特征明显的光谱波段为650~740 nm、780~800 nm.利用光谱角进行相似度计算,分析了阴影对光谱曲线的影响.在空间维,通过主成分分析和灰度共生矩阵的计算,得出了迷彩伪装纹理具有均匀性好、相关性强、复杂程度低等特点.研究结果为迷彩伪装的设计及识别提供了理论参考.In modern war, hyperspectral imaging technology is used to identify camouflage target. In order to strengthen the use of the information of hyperspectral images and find characteristics for camouflage identification, the hyperspectral characteristics and influencing factors of pattern painting camouflage are analyzed comprehensively. In spectral dimension, by analyzing the spectral curves extracted directly from hyperspectral images, 650~740 nm and 780~800 nm are determined to be optimal spectral bands for identification. Then the effect of shadows to spectral curves is discussed through the comparison of spectral curves. In spatial dimension, PCA and GLCM are used to calculate the texture of pattern painting camouflage, which displays good uniformity, strong correlation and low complexity. Results of this study is expected to provide a theoretical reference for the design and identification of the camouflage targets.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.200