帮助 关于我们

返回检索结果

结合扩展多属性剖面与快速局部RX算法的高光谱异常目标检测
Hyperspectral Abnormal Target Detection Based on Extended Multi-attribute Profile and Fast Local RX Algorithm

查看参考文献22篇

阿茹罕 1   原晓斌 2   慕晓冬 1 *   王静怡 3  
文摘 为进一步提高高光谱异常目标检测的速度与精度,提出一种基于扩展多属性剖面和改进的Reed-Xiaoli算法相结合的快速异常目标检测方法。通过数学形态学变换从高光谱图像中提取扩展多属性剖面,同时提出一种快速局部Reed-Xiaoli算法,利用矩阵求逆引理迭代更新协方差矩阵的逆,从而降低马氏距离的计算复杂度。将扩展多属性剖面与快速局部Reed-Xiaoli算法相结合,充分利用高光谱图像的光谱信息和空间信息,有效提高探测速度与精度。在3个不同的数据集上与其他经典异常目标检测方法进行比较,实验结果表明,所提算法AUC值分别为0.996 7、0.985 6、0.981 6,运算时间分别为21.218 1 s、15.192 8 s、32.337 9 s。该方法在检测精度和速度上都有明显的优势,具有良好的实用价值。
其他语种文摘 In order to further improve the speed and accuracy of hyperspectral abnormal target detection,a fast anomaly target detection method based on extended multi-attribute profiles and improved Reed-Xiaoli is proposed. Extended multi-attribute Profiles are extracted from the original hyperspectral images by mathematical morphological transformations. Moreover,a novel fast local Reed-Xiao algorithm is also proposed. Iteratively update inverse matrix of covariance using matrix inverse lemma,thereby reducing the computational complexity of the Mahalanobis distance. The combination of extended multi-attribute profiles and fast local Reed-Xiaoli detector effectively utilizes the spectral information and spatial information of hyperspectral images,it greatly improves the detection accuracy and reduce the running time. Experimental results on three real data sets show the AUC value of the algorithm in this paper is 0.996 7,0.985 6 and 0.981 6 respectively. The operation time is 21.218 1 s,15.192 8 s and 32.337 9 s respectively. The proposed method has obvious advantages in detection accuracy and speed,and has good practical value.
来源 光子学报 ,2021,50(9):0910002 【核心库】
DOI 10.3788/gzxb20215009.0910002
关键词 高光谱图像 ; 异常目标检测 ; 快速局部RX ; 扩展多属性剖面 ; Reed-Xiaoli ; 矩阵求逆引理
地址

1. 火箭军工程大学作战保障学院, 西安, 710025  

2. 中国科学院西安光学精密机械研究所, 西安, 710119  

3. 西安石油大学计算机学院, 西安, 710065

语种 中文
文献类型 研究性论文
ISSN 1004-4213
学科 机械、仪表工业;自动化技术、计算机技术
基金 国家自然科学基金
文献收藏号 CSCD:7068155

参考文献 共 22 共2页

1.  徐冬冬. 基于分层引导滤波与最近邻正则化子空间的高光谱图像分类. 光子学报,2020,49(4):0410004 CSCD被引 4    
2.  郭利强. 基于多标签共享子空间学习和内核脊回归的空谱分类算法. 光子学报,2020,49(5):0528001 CSCD被引 1    
3.  马世欣. 基于空谱联合聚类的改进核协同高光谱异常检测. 光子学报,2019,48(1):0110003 CSCD被引 3    
4.  王志威. 基于光谱空间重构的非监督最邻近规则子空间的高光谱异常检测. 光子学报,2020,49(6):0630004 CSCD被引 1    
5.  薛庆生. 静止轨道高光谱海洋水色仪光学系统设计. 光子学报,2020,49(5):0501001 CSCD被引 2    
6.  Reed I S. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Transactions on Acoustics Speech & Signal Processing,1990,38(10):1760-1770 CSCD被引 160    
7.  Li Z. Hyperspectral anomaly detection based on improved RX with CNN framework. IEEE International Symposium on Geoscience and Remote Sensing IGARSS,2019:2244-2247 CSCD被引 1    
8.  Hidalgo J A P. Efficient nonlinear RX anomaly detectors. IEEE Geoscience and Remote Sensing Letters,2021,18(2):231-235 CSCD被引 1    
9.  Ren L. A superpixel-based dual window RX for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters,2020,17(7):1233-1237 CSCD被引 3    
10.  Imani M. RX anomaly detector with rectified background. IEEE Geoscience and Remote Sensing Letters,2017,14(8):1313-1317 CSCD被引 8    
11.  Li W. Collaborative representation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1463-1474 CSCD被引 57    
12.  Ma N. A fast recursive collaboration representation anomaly detector for hyperspectral image. IEEE Geoscience and Remote Sensing Letters,2019,16(4):588-592 CSCD被引 2    
13.  Wu Z. hyperspectral anomaly detection using collaborative representation with PCA remove outlier. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018(11):1-5 CSCD被引 1    
14.  Sun W. Low-rank and sparse matrix decomposition-based anomaly detection for hyperspectral imagery. Journal of Applied Remote Sensing,2014,8(1):83641 CSCD被引 21    
15.  Zhang Y. A low-rank and sparse matrix decomposition-based Mahalanobis distance method for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing,2016,54(3):1-14 CSCD被引 36    
16.  Song S. Hyperspectral anomaly detection via graph dictionary-based low rank decomposition with texture feature extraction. Remote Sensing,2020,12(23):2072-4292 CSCD被引 1    
17.  Benediktsson J A. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):480-491 CSCD被引 86    
18.  Dalla Mura M. Morphological attribute profiles for the analysis of very high resolution images. IEEE Transactions on Geoscience and Remote Sensing,2010,48(10):3747-3762 CSCD被引 39    
19.  Dalla Mura M. Extended profiles with morphological attribute filters for the analysis of hyperspectral data. International Journal of Remote Sensing,2010,31(22):5975-5991 CSCD被引 24    
20.  Andika F. A Hyperspectral anomaly detection algorithm based on morphological profile and attribute filter with band selection and automatic determination of maximum area. Remote Sensing,2020,12(20):3387 CSCD被引 1    
引证文献 1

1 张蕾 利用光谱解混合的目标检测 光学精密工程,2023,31(21):3156-3166
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号