| 张丽丽,赵春晖,成宝芝.基于联合核协同的高光谱图像异常目标检测[J].光电子激光,2015,26(11):2154~2161 |
| 基于联合核协同的高光谱图像异常目标检测 |
| A joint kernel collaborative-representation-based approach for anomaly target detection of hyperspectral images |
| 投稿时间：2015-07-08 |
| DOI： |
| 中文关键词: 高光谱图像 异常目标检测 核协同 稀疏差异指数 |
| 英文关键词:hyperspectral image anomaly target detection kernel collaborative re presentation sparsity divergence index |
| 基金项目:国家自然科学基金(61405041)、黑龙江省自然科学基金(ZD201216)、哈尔滨市优秀学科带头人基金(RC2013XK009003)、中国博士后基金(2014M551221) 、中央高校基础研究基金(HEUCF1508)、黑龙江省博士后基金资助项目(LBH-Z14062)和大庆师 范学院青年基金(12ZR15)资助项目 (1.哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨 150001； 2.大庆师范学院 机电工程学院, 黑龙江大庆 163712； 3.哈尔滨工程大学计算机科学与技术学院,黑龙江哈尔滨 150001) |
|
| 摘要点击次数: 1208 |
| 全文下载次数: 0 |
| 中文摘要: |
| 在目前的高光谱图像异常目标检测算法中,通常 只考虑高光谱图像的光谱特性而忽 略其空间 特性,针对这一问题,提出了基于联合核协同的稀疏差异指数的检测算法。本文算法将核协 同与稀疏差异指数表示方法相结合,分别提出了光谱核协同和空间核协同的 稀疏差异 指数表示模型,进而提出了一种联合核协同的稀疏差异指数表示模型。在模拟的 高光谱图 像数据中,讨论了双窗口设计对所提出算法的检测结果的影响；在真实的AVIRIS高光谱图像 仿真实 验中,分析了不同波段选择及主成分分析对检测结果的影响。结果表 明,所提出的算法检测精度高,虚警概 率低。 |
| 英文摘要: |
| An anomaly target detection algorithm based on sparsity divergence index of joint kernel collaborative-repr esentation is proposed in order to further improve the detection effect of abnormal target in the hyperspectral ima ge.Firstly,the kernel collaborative-representation-based model is introduced; Secondl y,in addition to the high spectral correlation,the spatial correlation is taken into full consideration at the sam e time.By combining with the representation method of the sparsity divergence index,the sparsity divergence index models based on spectral and spatial kernel collaborative-representations are proposed respectively.Then,a new sparsity divergence index representation model based on joint kernel collaborative-repre sentation is proposed.At last,by the experiment with simulated hyperspectral image data,we discuss the effects of dual window design on the detection results of the proposed algorithm.In the simulation experiments carried out with real AVIRIS hyperspectral image data,we analyze the effects of the selection of different bands and principal component analysis on the detection results.The proposed algorithm is compared with the l ocal RX algorithm,local kernel RX algorithm,the algorithm based on collaborative representation,the algorithm based on local sparsity divergence and the algorithm based on sparsity divergence index weighting.The e xperimental results show that the proposed algorithm has higher precision and lower false alarm probability. |
| 查看全文 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|