基于逐行处理的高光谱实时异常目标检测

实时处理可以缓解海量高光谱数据在存储及下行传输方面带来的巨大压力, 在高光谱异常检测领域引起了研究人员的广泛关注。高光谱成像传感器通过推扫获取数据的方式已成为主流, 因此, 提出了一种基于逐行处理框架的高光谱实时异常目标检测算法。将局部因果窗模型引入Reed-Xiaoli异常检测算法中, 通过滑动局部因果窗来检测异常目标, 保证了实时处理的因果性。针对矩阵求逆过程复杂度过大的问题, 在卡尔曼滤波器递归思想的基础上, 利用Woodbury求逆引理, 由前一时刻数据状态信息迭代更新当前数据的状态信息, 避免了大矩阵的求逆运算, 减少了算法的计算量。利用模拟和真实高光谱数据进行实验, 结果表明, 在保持检测精度不变的前提下, 提出的实时算法的运算效率相比于原始算法得到显著提高。

Abstract

Real-time processing can reduce the pressure of data storage and downlink transmission caused by the ever-expending hyperspectral dataset, which has received more and more attention in hyperspectral anomaly detection. Since acquiring data with pushbroom has become main stream for hyperspectral imaging sensors, a real-time anomaly target detection method is proposed based on the framework of progressive line processing. In order to make sure the causality of real-time processing, the local causal window model is introduced into the Reed-Xiaoli anomaly detection algorithm, and the sliding local causal window is used to detect anomaly targets. In terms of the high computational complexity caused by the inversion of matrix, the recursive principle of the Kalman filter and the Woodbury′s lemma are employed to update the status information of current data through iterating data status information at the previous moment, which avoids the inversion of large matrix. The simulated and real hyperspectral data are adopted for the experiment. The results show that under the premise of maintaining the detection accuracy, the proposed real-time algorithm improves the processing efficiency significantly compared with the original algorithm.

参考文献

[1] 王晓飞, 阎秋静, 张钧萍, 等. 基于相关向量机的高光谱图像超分辨率算法［J］. 中国激光, 2014, 41(s1): s114001.

Wang Xiaofei, Yan Qiujing, Zhang Junping, et al. Super-resolution reconstruction algorithm based on relevance vector machine for hyperspectral image［J］. Chinese J Lasers, 2014, 41(s1): s114001.

[2] 王晓飞, 阎秋静. 基于集成学习的高光谱图像一类分类算法［J］. 光学学报, 2014, 34(s2): s211002.

Wang Xiaofei, Yan Qiujing. An ensemble learning algorithm for one-class classification of hyperspectral images［J］. Acta Optica Sinica, 2014, 34(s2): s211002.

[3] 赵春晖, 尤伟, 齐滨, 等. 采用多项式递归核的高光谱遥感异常实时检测算法［J］. 光学学报, 2016, 36(2): 0228002.

Zhao Chunhui, You Wei, Qi Bin, et al. Real-time anomaly detection algorithm for hyperspectral remote sensing by using recursive polynomial kernel function［J］. Acta Optica Sinica, 2016, 36(2): 0228002.

[4] 王立国, 赵春晖. 高光谱图像处理技术［M］. 北京: 国防工业出版社, 2013.

Wang Liguo, Zhao Chunhui. Hyperspectral image processing technology［M］. Beijing: National Defence Industry Press, 2013.

[5] 张兵, 高连如. 高光谱图像分类与目标探测［M］. 北京: 科学出版社, 2011.

Zhang Bing, Gao Lianru. Hyperspectral image classification and target detection［M］. Beijing: Science Press, 2011.

[6] Reed I S, Yu X. Adaptive multi-band CFAR detection of an optical pattern with unknown spectral distribution［J］. IEEE Transactions on Acoustics Speech and Signal Processing, 1990, 38(10): 1760-1770.

[7] Chen S Y, Wang Y L, Wu C C, et al. Real-time causal processing of anomaly detection for hyperspectral imagery［J］. IEEE Transactions on Aerospace and Electronuc Systems, 2014, 50(2): 1511-1534.

[8] Chang C I, Li Y, Hobbs M C, et al. Progressive band processing of anomaly detection in hyperspectral imagery［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7): 3558-3571.

[9] Rossi A, Acito N, Diani M, et al. RX architectures for real-time anomaly detection in hyperspectral images［J］. Journal of Real-Time Image Processing, 2014, 9(3): 503-517.

[10] 张贤达. 矩阵分析与应用［M］. 北京: 清华大学出版社, 2004.

Zhang Xianda. Matrix analysis and applications［M］. Beijing: Tsinghua University Press, 2004.

[11] Chang C I, Wang Y L, Chen S Y. Anomaly detection using causal sliding windows［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7): 3260-3270.

[12] Kossi A, Acito N, Diani M, et al. RX architecture for real-time anomaly detection in hyperspectral images［J］. Journal of Real-Time Image Processing, 2014, 9(3): 503-517.

[13] Wang J, Chang C I. Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery［J］. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44( 9): 2601-2616.

[14] Chang Y C, Ren H, Chang C I, et al. How to design synthetic images to validate and evaluate hyperspectral imaging algorithms［C］. SPIE, 2008, 6966: 69661P.

赵春晖, 邓伟伟, 姚淅峰. 基于逐行处理的高光谱实时异常目标检测[J]. 光学学报, 2017, 37(1): 0128002. Zhao Chunhui, Deng Weiwei, Yao Xifeng. Hyperspectral Real-Time Anomaly Target Detection Based on Progressive Line Processing[J]. Acta Optica Sinica, 2017, 37(1): 0128002.

基于逐行处理的高光谱实时异常目标检测

关于本站 Cookie 的使用提示

全站搜索

基于逐行处理的高光谱实时异常目标检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索