Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method

DONG Yanni; DU Bo; ZHANG Lefei; ZHANG Liangpei

doi:10.13203/j.whugis20150504

Volume 43 Issue 8

Aug. 2018

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2018 > 43(8): 1271-1277. > DOI: 10.13203/j.whugis20150504

DONG Yanni, DU Bo, ZHANG Lefei, ZHANG Liangpei. Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method[J]. Geomatics and Information Science of Wuhan University, 2018, 43(8): 1271-1277. DOI: 10.13203/j.whugis20150504

Citation:

PDF (10871 KB)

Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method

1.
Institute of Geophysics & Geomatics, China University of Geosciences, Wuhan 430074, China
2.
School of Computer Science, Wuhan University, Wuhan 430072, China
3.
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

Funds:

The National Basic Research Program 2012CB719905

the National Natural Science Foundation of China 61471274

the National Natural Science Foundation of China 41431175

the Natural Science Foundation of Hubei Province 2014CFB193

the Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan) CUG 170687

More Information

Author Bio:
DONG Yanni, PhD, associate professor, specializes in hyperspectral image processing and metric learning. E-mail: dongyanni@cug.edu.cn
Corresponding author:
DU Bo, PhD, professor. E-mail:gunspace@163.com
Received Date: September 18, 2016
Published Date: August 04, 2018

Graphical Abstract

Abstract

Abstract

The classical target detection methods may only perform well with certain assumptions. To overcome the shortcomings, this paper proposes a novel local decision adaptive information-theoretic metric learning (LA-ITML) target detector. Firstly, the proposed method uses the ITML method as the objective function for learning a Mahalanobis distance to separate similar and dissimilar point-pairs. Then, a locally decision adaptive constraint is applied to shrink the distances between samples of similar pairs and expand the distances between samples of dissimilar pairs. Finally, we can make the detection decision by considering both the threshold and the changes between the distances before and after metric learning. The experimental results demonstrate that the proposed method can obviously separate target samples from background ones and out performs both the state-of-the-art target detection algorithms and the other classical metric learning methods.
- target detection,
- metric learning,
- decision rule,
- locally adaptive,
- hyperspectral images

FullText(HTML)

References (22)

References

[1]	Manolakis D, Shaw G. Detection Algorithms for Hyperspectral Imaging Applications[J]. IEEE Signal Processing Magazine, 2002, 19(1):29-43 doi: 10.1109/79.974724
[2]	Du B, Zhang L P. Target Detection Based on a Dynamic Subspace[J]. Pattern Recognition, 2014, 47(1):344-358 doi: 10.1016/j.patcog.2013.07.005
[3]	Harsanyi J C. Detection and Classification of Subpixel Spectral Signatures in Hyperspectral Image Sequences[D]. Baltimore: University of Maryland Baltimore County, 1993
[4]	Kraut S, Scharf L L, McWhorter L T. AdaptiveSubspace Detectors[J]. IEEE Transactions on Signal Processing, 2001, 49(1):1-16 doi: 10.1109/78.890324
[5]	Kraut S, Scharf L L. The CFAR Adaptive Subspace Detector is a Scale-Invariant GLRT[J]. IEEE Transactions on Signal Processing, 1999, 47(9):2538-2541 doi: 10.1109/78.782198
[6]	陈勇, 杜博, 张乐飞.一种融合光谱匹配和张量分析的高分辨率遥感影像目标探测器[J].武汉大学学报·信息科学版, 2013, 38(3):274-277 http://ch.whu.edu.cn/CN/Y2013/V38/I3/274 Chen Yong, Du Bo, Zhang Lefei. A Hybrid Detector for High Resolution Remote Sensing Image Based on Spectral Matching and Tensor Analysis[J]. Geomatics and Information Science of Wuhan University, 2013, 38(3):274-277 http://ch.whu.edu.cn/CN/Y2013/V38/I3/274
[7]	Xiang S M, Nie F P, Zhang C S. Learning a Maha-lanobis Distance Metric for Data Clustering and Classification[J]. Pattern Recognition, 2008, 41(12):3600-3612 doi: 10.1016/j.patcog.2008.05.018
[8]	Plaza A, Martínez P, Plaza J, et al. DimensionalityReduction and Classification of Hyperspectral Image Data Using Sequences of Extended Morphological Transformations[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3):466-479 doi: 10.1109/TGRS.2004.841417
[9]	Capobianco L, Garzelli A, Camps-Valls G. Target Detection with Semisupervised Kernel Orthogonal Subspace Projection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(11):3822-3833 doi: 10.1109/TGRS.2009.2020910
[10]	Chen Y, Nasrabadi N M, Tran T D. Sparse Representation for Target Detection in Hyperspectral Imagery[J]. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(3):629-640 doi: 10.1109/JSTSP.2011.2113170
[11]	Dong Y N, Zhang L P, Zhang L F, et al. Maximum Margin Metric Learning Based Target Detection for Hyperspectral Images[J]. ISPRS Journal of Photogrammetry Remote Sensing, 2015, 108:138-150 doi: 10.1016/j.isprsjprs.2015.07.003
[12]	Du B, Zhang L P. A Discriminative Metric Learning Based Anomaly Detection Method[J]. IEEE Tran-sactions on Geoscience and Remote Sensing, 2014, 52(11):6844-6857 doi: 10.1109/TGRS.2014.2303895
[13]	Xing E P, Ng A Y, Jordan M I, et al. Distance Metric Learning, with Application to Clustering with Side-information[C]. Advances in Neural Information Processing Systems, Vancouver, Canada, 2002
[14]	Tao D, Li X, Wu X, et al. General Tensor Discri-minant Analysis and Gabor Features for Gait Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(10):1700-1715 doi: 10.1109/TPAMI.2007.1096
[15]	Davis J, Kulis V B, Jain P, et al. Information-Theoretic Metric Learning[C]. The 24th International Conference on Machine Learning, Corvallis, USA, 2007
[16]	Davis J V, Dhillon I S. Differential Entropic Clustering of Multivariate Gaussians[C]. The 19th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2006
[17]	Li Z, Chang S Y, Liang F, et al. Learning Locally-Adaptive Decision Functions for Person Verification[C]. 2013 IEEE Conference on Computer Vision and Pattern Reognition, Portland, USA, 2013
[18]	Tao D, Tang X, Li X, et al. Asymmetric Bagging and Random Subspace for Support Vector Machines-Based Relevance Feedback in Image Retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(7):1088-1099 doi: 10.1109/TPAMI.2006.134
[19]	Tao D, Li X, Wu X, et al. Geometric Mean for Subspace Selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):260-274 doi: 10.1109/TPAMI.2008.70
[20]	Goldberger J, Hinton G, Roweis S, et al. Neighbourhood Components Analysis[C]. Advances in Neural Information Processing Systems, Cambridge, United Kingdom, 2005
[21]	Dong Y N, Du B, Zhang L P. Target Detection Based on Random Forest Metric Learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(4):1830-1838 doi: 10.1109/JSTARS.2015.2416255
[22]	Dong Y N, Du B, Zhang L F, et al. Dimensionality Reduction and Classification of Hyperspectral Images Using Ensemble Discriminative Local Metric Learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5):2509-2524 doi: 10.1109/TGRS.2016.2645703

[1]	XIAO Tianyuan, LIU Pengcheng, AI Tinghua, LI Jingzhong. A Fractal Description and Multi-scale Expression Method of Fourier Information Metrics[J]. Geomatics and Information Science of Wuhan University, 2020, 45(1): 119-125. DOI: 10.13203/j.whugis20180336
[2]	DIAN Yuanyong, YANG Guang, FANG Shenghui. Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2017, 42(3): 362-368. DOI: 10.13203/j.whugis20140952
[3]	LIU Li, LI Jinling. Determination and Analysis of Station Parameters ofthe Chinese VLBI Network[J]. Geomatics and Information Science of Wuhan University, 2014, 39(3): 262-266. DOI: 10.13203/j.whugis20120005
[4]	ZHANG Zhibin, WANG Guangli, LIU Xiang, TANG Zhenghong. Analysis of EOP Determination via Chinese VLBI Network[J]. Geomatics and Information Science of Wuhan University, 2013, 38(8): 911-915.
[5]	WEI Erhu, ZHANG Qi. On Length of Day with 1985-2010 VLBI Observations[J]. Geomatics and Information Science of Wuhan University, 2012, 37(9): 1020-1023.
[6]	LIN Hui, LIANG Liang, DU Peijun, SUN Huasheng. Image Registration Based on Fourier-Mellin Transform[J]. Geomatics and Information Science of Wuhan University, 2012, 37(6): 649-652.
[7]	WEI Erhu, LI Xuechuan, YI Hui, LIU Jingnan. On EOP Parameters Based on 2008 VLBI Observation Data[J]. Geomatics and Information Science of Wuhan University, 2010, 35(8): 988-990.
[8]	WEI Erhu, LIU Jingnan, PAN Peijing. On Data Processing with Last Three Years of VLBI Observation[J]. Geomatics and Information Science of Wuhan University, 2008, 33(12): 1275-1278.
[9]	LI Yingbing, XU Shaoquan, ZHANG Yongjun, ZHANG Xiaohong. The Application of Spectrum Analysis in GPS Auto-monitoring System[J]. Geomatics and Information Science of Wuhan University, 2001, 26(4): 343-348.
[10]	Zhang Genshou, Zhu Guorui. Analysis and Study of the Areal Shape on Map[J]. Geomatics and Information Science of Wuhan University, 1994, 19(1): 29-36.

Cited By

Cited by

Periodical cited type(7)

1.	牟希农. 基于小波域马尔可夫随机场的医学影像图像提取实现研究. 贵州大学学报(自然科学版). 2020(01): 74-77 .
2.	陈志坤，江俊君，姜鑫维，白露，蔡之华. 一种基于改进双边滤波的鲁棒高光谱遥感图像特征提取方法. 武汉大学学报(信息科学版). 2020(04): 504-510 .
3.	郭利强，孟庆超. 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(05): 121-133 .
4.	李玉，甄畅，石雪，赵泉华. 基于熵加权K-means全局信息聚类的高光谱图像分类. 中国图象图形学报. 2019(04): 630-638 .
5.	曲海成，郭月，王媛媛. 基于优势集聚类和马尔科夫随机场的高光谱图像分类算法. 国土资源遥感. 2019(02): 24-31 .
6.	职露，余旭初，邹滨，刘冰. 多层级二值模式的高光谱影像空-谱分类. 武汉大学学报(信息科学版). 2019(11): 1659-1666 .
7.	韦春桃，赵平，肖博林，白风，李小勇，杨晚芸. 结合双树复小波纹理特征和MRF模型的遥感图像分割. 测绘通报. 2019(10): 40-45 .

Other cited types(8)

Get Citation

PDF

XML

Article views (1997) PDF downloads (300) Cited by(15)

Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method

Abstract

References

Related Articles

Cited by

Periodical cited type(7)

Other cited types(8)

Catalog

Related

Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method

Abstract

References

Related Articles

Cited by

Periodical cited type(7)

Other cited types(8)

Catalog

Related

Export File

Citation

Format

Content