基于张量表示的高光谱图像目标检测
Tensor representation based target detection for hyperspectral imagery
查看参考文献30篇
|
文摘
|
高光谱图像目标检测作为一个研究热点在军事和民用方面的应用越来越广泛。为了能同时利用高光谱图像数据的空谱信息,本文提出一种新的基于张量表示的高光谱图像目标检测算法。算法使用CP(Canonical Polyadic)张量分解技术和张量块分解(Block Term Decomposition,BTD)分别对高光谱数据进行盲源分析,提取了有效的局部图像块空谱特征,建立了一个基于稀疏表示和协作表示的检测模型,针对多种类型背景复杂的场景数据进行实验,并与当前流行的目标检测算法进行比较。从可视化检测结果来看,本文算法在复杂背景和强噪声环境下,有效提取了空谱特征,对背景具有较好的抑制能力,检测的目标显著。此外,本文从接收机操作曲线(Receiver Operating Characteristic Curve,ROC)和ROC曲线下面积(Area Under Curve,AUC)等定量指标分析算法性能。以较为流行的Sandiego图像为例,在10%的虚警率下,本文算法取得90%的检测精度,AUC大于0.95。本文算法相较几种流行算法而言具有较高的检测精度,更强的鲁棒性。 |
|
其他语种文摘
|
Target detection for Hyperspectral Images (HSIs)is gaining importance owing to its important military and civilian applications.This study proposed a novel target detection algorithm for HSIs based on tensor representation.The algorithm employed tensor analysis including CP and tensor block decompositions to implement blind source separation on hyperspectral data.First,effective spatial and spectral features of the blocks of local images were extracted.Then,a detection model based on sparse and collaborative representations was established.Experiments were conducted to evaluate the performance of our approach under multiple scenes with complex backgrounds.From the visual representation of the results,it can be concluded that the proposed approach effectively extracts the spatial-spectral features from scenes with strong noise and complex backgrounds.The approach has good ability to suppress the background and the target is salient.In addition,the performance of the approach is evaluated using quantitative metrics such as Receiver Operating Curve(ROC)and area under the ROC curve(AUC).Considering the popular HSI image of San Diego as an example,the approach achieves 90% detection rate with a false alarm rate of 10%,and the AUC is greater than 0.95.Hence,our approach outperforms other popular approaches. |
|
来源
|
光学精密工程
,2019,27(2):488-498 【核心库】
|
|
DOI
|
10.3788/ope.20192702.0488
|
|
关键词
|
目标检测
;
高光谱图像
;
张量表示
;
特征提取
;
协作表示
|
|
地址
|
1.
中国科学院西安光学精密机械研究所, 陕西, 西安, 710119
2.
西安交通大学电子信息与工程学院, 陕西, 西安, 710049
3.
中国科学院大学, 北京, 100049
4.
中国科学院地球环境研究所, 陕西, 西安, 710016
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1004-924X |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金资助项目
;
陕西省自然科学基金
|
|
文献收藏号
|
CSCD:6442078
|
参考文献 共
30
共2页
|
|
1.
唐意东. 高光谱图像自适应核联合表示异常检测.
强激光与粒子束,2015,27(9):49-55
|
被引
3
次
|
|
|
|
|
2.
赵春晖. 基于StOMP稀疏方法的高光谱图像目标检测.
哈尔滨工程大学学报,2015,36(7):992-996
|
被引
6
次
|
|
|
|
|
3.
赵春晖. 基于稀疏表示的高光谱图像增殖快速算法.
黑龙江大学自然科学学报,2017,34(1):95-102
|
被引
1
次
|
|
|
|
|
4.
凌强. 联合表示求解二元假设模型的高光谱目标检测.
电子学报,2016,44(11):2633-2638
|
被引
1
次
|
|
|
|
|
5.
Bitar A W. Sparse and low-rank decomposition for automatic target detection in hyperspectral imagery.
Electrical-Engineering and Systems Science,2017,24(11)
|
被引
1
次
|
|
|
|
|
6.
Niu Y. Hyperspectral anomaly detection based on low-rank representation and learned dictionary.
Remote Sensing,2016,8(4):289
|
被引
2
次
|
|
|
|
|
7.
Nasrabadi N M. Hyperspectral target detection:an overview of current and future challenges.
IEEE Signal Processing Magazine,2014,31(1):34-44
|
被引
27
次
|
|
|
|
|
8.
Akbari D.
Support vector machine for target detection in hyperspectral images. TS06I-Remote Sensing II,6135,2012:10
|
被引
1
次
|
|
|
|
|
9.
黄鸿. 空-谱协同流形重构的高光谱影像分类.
光学精密工程,2018,26(7):1827-1836
|
被引
8
次
|
|
|
|
|
10.
Makantasisk.
Deep learning-based man-made object detection from hyperspectral data,2015:717-727
|
被引
1
次
|
|
|
|
|
11.
Zhang L. Hyperspectral remote sensing image subpixel target detection based on supervised metric learning.
IEEE Transactions on Geoscience and Remote Sensing,2014,52(8):4955-4965
|
被引
6
次
|
|
|
|
|
12.
.
Transter learning
|
被引
1
次
|
|
|
|
|
13.
Du B. Unsupervised transfer learning for target detection from hyperspectral images.
Neurocomputing,2013,120:72-82
|
被引
7
次
|
|
|
|
|
14.
Dong Y. Local decision maximum margin metric learning for hyperspectral target detection.
2015 IEEE International Geoscience and Remote Sensing Symposium,2015:397-400
|
被引
1
次
|
|
|
|
|
15.
Ren Y. Hyperspectral image spectral-spatial feature extraction via tensor principal component analysis.
IEEE Geoscience and Remote Sensing Letters,2017,14(9):1431-1435
|
被引
1
次
|
|
|
|
|
16.
谷延锋. 高分辨率航空遥感高光谱图像稀疏张量目标检测.
测绘通报,2015(1):31-38
|
被引
1
次
|
|
|
|
|
17.
Zhang Q. Tensor methods for hyperspectral data analysis:a space object material identification study.
Journal of the Optical Society of America A,2008,25(12):3001-3012
|
被引
2
次
|
|
|
|
|
18.
Veganzonesma. Nonnegative tensor CP decomposition of hyperspectral data.
IEEE Transactions on Geoscience and Remote Sensing,2016,54(5):2577-2588
|
被引
5
次
|
|
|
|
|
19.
Liu Y. Tensor matched subspace detector for hyperspectral target detection.
IEEE Transactions on Geoscience and Remote Sensing,2017,55(4):1967-1974
|
被引
1
次
|
|
|
|
|
20.
Zhang X. Target representation in hyperspectral images based on tensor block term decomposition.
2015 8th International Congress on Image and Signal Processing,2015:793-798
|
被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问