Target detection using spectral unmixing

ZHANG Lei; QIAO Kai; WU Yinhua; LI Siyuan

doi:10.37188/OPE.20233121.3156

您当前的位置：

首页 >

文章列表页 >

Target detection using spectral unmixing

Information Sciences | 更新时间：2023-11-16

- Target detection using spectral unmixing
- Optics and Precision Engineering Vol. 31, Issue 21, Pages: 3156-3166(2023)
- 作者机构：
  
  1.北京跟踪与通信技术研究所，北京 100094
  2.西安工业大学，陕西西安 710021
  3.中国科学院西安光学精密机械研究所，陕西西安710119
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233121.3156
  CLC：
扫描看全文
张蕾,乔凯,吴银花等.利用光谱解混合的目标检测[J].光学精密工程,2023,31(21):3156-3166.

ZHANG Lei,QIAO Kai,WU Yinhua,et al.Target detection using spectral unmixing[J].Optics and Precision Engineering,2023,31(21):3156-3166.
张蕾,乔凯,吴银花等.利用光谱解混合的目标检测[J].光学精密工程,2023,31(21):3156-3166. DOI： 10.37188/OPE.20233121.3156.

ZHANG Lei,QIAO Kai,WU Yinhua,et al.Target detection using spectral unmixing[J].Optics and Precision Engineering,2023,31(21):3156-3166. DOI： 10.37188/OPE.20233121.3156.

摘要

高光谱目标检测中背景信息的统计往往受到目标信息的干扰，而高光谱图像中存在的大量混合像元会进一步加深这一干扰。为了准确统计背景信息、显著降低目标像元对背景统计信息的干扰，提出了一种利用光谱解混合的目标检测算法，通过光谱解混合和目标相似性判断，获取目标端元对应丰度系数，并与光谱夹角系数相结合生成合理的背景加权系数，进行加权约束最小能量算子（CEM）目标检测，从而有效提高混合像元的背景信息统计准确度；利用目标端元对应丰度系数和光谱夹角系数生成初步的目标检测结果，与加权CEM目标检测结果相融合进行进一步优化，有效提高算法稳定性，同时再次提高目标检测精度。实验结果表明：对于模拟高光谱图像和真实高光谱图像，本文算法均得到了较好的目标检测效果，算法稳定性较强，且有效提高了目标检测精度，相比传统CEM算法、基于光谱角的加权CEM算法、归一化丰度系数作为目标结果，AUC值分别平均提高了0.071 2，0.031 2和0.015 0，在高光谱应用中具有较强的实用性。

Abstract

The statistics of background information in hyperspectral target detection are often interfered by target information， and the presence of a large number of mixed pixels in hyperspectral images will further deepen this interference. In this study， we proposed a target detection algorithm using spectral unmixing to accurately calculate background information and significantly reduce the interference of target pixels on background statistical information. First， we obtained the abundance coefficient corresponding to the target end member by spectral unmixing and target similarity judgment. We combined it with the spectral angle coefficient to generate a reasonable background weighting coefficient for weighted constrained energy minimization （CEM） target detection， effectively improving the statistical accuracy of background information of mixed pixels. Second， we generated a preliminary result of target detection by utilizing the abundance coefficient corresponding to the target end member and spectral angle coefficient and fused with the weighted CEM target detection result to optimize further， effectively improving the robustness of the algorithm and target detection accuracy. Experimental results showed that the algorithm proposed in this study has good target detection performance for simulated or real hyperspectral images. The algorithm has strong robustness and effectively improves target detection accuracy. Compared with the traditional CEM algorithm， weighted CEM algorithm based on spectral angle， and normalized abundance coefficient as the target result the AUC of this study was promoted by an average of 0.071 2， 0.031 2， and 0.015 0， respectively. The proposed algorithm has strong practicability in hyperspectral applications.

关键词

高光谱图像目标检测光谱解混合丰度光谱角

Keywords

hyperspectral imagetarget detectionhyperspectral unmixingabundancespectral angle

references

时旭，李远，黄鸿. 面向高光谱显微图像血细胞分类的空-谱可分离卷积神经网络［J］. 光学精密工程， 2022， 30（8）：960-969. doi: 10.37188/ope.20223008.0960http://dx.doi.org/10.37188/ope.20223008.0960

SHI X， LI Y， HUANG H. Spatial-spectral separable convolutional neural network for cell classification of hyperspectral microscopic images［J］. Optics and Precision Engineering， 2022， 30（8）：960-969.（in Chinese）. doi: 10.37188/ope.20223008.0960http://dx.doi.org/10.37188/ope.20223008.0960

于磊，陈结祥，薛辉，等. 用于沿海水色探测的机载紫外-可见-近红外高光谱成像仪［J］. 光学精密工程， 2018， 26（10）： 2363-2370. doi: 10.3788/ope.20182610.2363http://dx.doi.org/10.3788/ope.20182610.2363

YU L， CHEN J X， XUE H， et al. Hyper-spectral imaging sensor in UV-VIS-NIR region in air for coastal ocean observation［J］. Opt. Precision Eng.， 2018， 26（10）： 2363-2370. （in Chinese）. doi: 10.3788/ope.20182610.2363http://dx.doi.org/10.3788/ope.20182610.2363

漆成莉，周方，吴春强，等. 风云三号红外高光谱探测仪的光谱定标［J］. 光学精密工程， 2019， 27（4）：747-755. doi: 10.3788/ope.20192704.0747http://dx.doi.org/10.3788/ope.20192704.0747

QI CH L， ZHOU F， WU CH Q， et al. Spectral calibration of Fengyun-3 satellite high-spectral resolution infrared sounder［J］. Optics and Precision Engineering， 2019， 27（4）：747-755.（in Chinese）. doi: 10.3788/ope.20192704.0747http://dx.doi.org/10.3788/ope.20192704.0747

SONG S G， GIBSON D， AHMADZADEH S， et al. Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications［J］. Applied Optics， 2020， 59（5）： A167-A175. doi: 10.1364/ao.378269http://dx.doi.org/10.1364/ao.378269

张兵. 高光谱图像处理与信息提取前沿［J］. 遥感学报， 2016， 20（5）：1062-1090. doi: 10.11834/jrs.20166179http://dx.doi.org/10.11834/jrs.20166179

ZHANG B. Advancement of hyperspectral image processing and information extraction［J］. Journal of Remote Sensing， 2016， 20（5）：1062-1090.（in Chinese）. doi: 10.11834/jrs.20166179http://dx.doi.org/10.11834/jrs.20166179

MORALES-SILLERO A， PIERNA J A F， SINNAEVE G， et al. Quantification of protein in wheat using near infrared hyperspectral imaging： performance comparison with conventional near infrared spectroscopy［J］. Journal of Near Infrared Spectroscopy， 2018， 26（3）： 186-195. doi: 10.1177/0967033518780506http://dx.doi.org/10.1177/0967033518780506

王勃凡，赵海涛. 基于径向基激活函数的高光谱小目标检测［J］. 光学学报， 2021， 41（23）： 2311001. doi: 10.3788/AOS202141.2311001http://dx.doi.org/10.3788/AOS202141.2311001

WANG B F， ZHAO H T. Hyperspectral small target detection based on radial basis function［J］. Acta Optica Sinica， 2021， 41（23）： 2311001.（in Chinese）. doi: 10.3788/AOS202141.2311001http://dx.doi.org/10.3788/AOS202141.2311001

杨帅，计璐艳，耿修瑞. 基于滤波张量分析的高光谱目标检测方法［J］. 中国科学院大学学报， 2022， 39（5）：684-694.

YANG SH， JI L Y， GENG X R. Hyperspectral target detection method based on filter tensor analysis［J］. Journal of University of Chinese Academy of Sciences， 2022， 39（5）：684-694.（in Chinese）

阿茹罕，原晓斌，慕晓冬，等. 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［J］. 光子学报， 2021， 50（9）： 0910002.

A R H， YUAN X B， MU X D， et al. Hyperspectral abnormal target detection based on extended multi-attribute profile and fast local RX algorithm［J］. Acta Photonica Sinica， 2021， 50（9）： 0910002.（in Chinese）

张小荣，胡炳樑，潘志斌，等. 基于张量表示的高光谱图像目标检测［J］. 光学精密工程， 2019， 27（2）： 488-498. doi: 10.3788/ope.20192702.0488http://dx.doi.org/10.3788/ope.20192702.0488

ZHANG X R， HU B L， PAN ZH B， et al. Tensor representation based target detection for hyperspectral imagery［J］. Optics and Precision Engineering， 2019， 27（2）： 488-498.（in Chinese）. doi: 10.3788/ope.20192702.0488http://dx.doi.org/10.3788/ope.20192702.0488

CHONG D， HU B， GAO H， et al.. Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism［J］. Applied Optics， 2021， 60（26）：8109-8119. doi: 10.1364/ao.432704http://dx.doi.org/10.1364/ao.432704

WANG Y T， HUANG S Q， LIU Z G， et al. Locality preserving projection based on endmember extraction for hyperspectral image dimensionality reduction and target detection［J］. Applied Spectroscopy， 2016， 70（9）： 1573-1581. doi: 10.1177/0003702816665992http://dx.doi.org/10.1177/0003702816665992

HAN S H， KEREKES J， HIGBEE S， et al. Band selection method for subpixel target detection using only the target reflectance signature［J］. Applied Optics， 2019， 58（11）： 2981-2993. doi: 10.1364/ao.58.002981http://dx.doi.org/10.1364/ao.58.002981

HARSANYI J C. Detection and Classification of Subpixel Spectral Signatures in Hyperspectral Image Sequences［D］. Baltimore County：University of Maryland， 1993.

耿修瑞. 高光谱遥感图像目标探测与分类技术研究［D］. 北京：中国科学院研究生院（遥感应用研究所）， 2005.

GENG X R. Research on Target Detection and Classification Technology of Hyperspectral Remote Sensing Images［D］. Beijing： Institute of Remote Sensing Applications， Chinese Academy of Sciences， 2005. （in Chinese）

杨桄，田张男，李豪，等. 基于线性解混的高光谱图像目标检测研究［J］. 激光技术， 2020， 44（2）：43-147. doi: 10.7510/jgjs.issn.1001-3806.2020.02.001http://dx.doi.org/10.7510/jgjs.issn.1001-3806.2020.02.001

YANG G， TIAN ZH N， LI H， et al. Research of target detection of hyperspectral images in complex background based on linear unmixing［J］. Laser Technology， 2020， 44（2）：43-147. （in Chinese）. doi: 10.7510/jgjs.issn.1001-3806.2020.02.001http://dx.doi.org/10.7510/jgjs.issn.1001-3806.2020.02.001

CHANG C I， REN H， CHANG C C， et al. Estimation of subpixel target size for remotely sensed imagery［J］. IEEE Transactions on Geoscience and Remote Sensing， 2004， 42（6）： 1309-1320. doi: 10.1109/tgrs.2004.826559http://dx.doi.org/10.1109/tgrs.2004.826559

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Mandibular fracture detection with 3M-YOLOv5 network based on enhanced feature extraction capability

Lightweight target detection network for UAV platforms

Visual composite positioning for precision microassembly

Partial optimal transport-based domain adaptation for hyperspectral image classification

Multi-graph regularized multi-kernel nonnegative matrix factorization for hyperspectral image unmixing

Related Author

No data

Related Institution

School of Medical Information & Engineering， Ningxia Medical University

Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission， North Minzu University

College of Computer Science and Engineering， North Minzu University

National and Local Joint Engineering Ｒesearch Center of Space Photoelectric Technology， Changchun University of Science and Technology

School of Electronics and In formation Engineering， Changchun University of Science and Technology

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰