Sparse Representation Based Band Selection for Hyperspectral Imagery Target Detection

TANG Yi-dong; HUANG Shu-cai; XUE Ai-jun

doi:10.3969/j.issn.0372-2112.2017.10.009

您当前的位置：

首页 >

文章列表页 >

Sparse Representation Based Band Selection for Hyperspectral Imagery Target Detection

更新时间：2025-07-16

- Sparse Representation Based Band Selection for Hyperspectral Imagery Target Detection
- Acta Electronica Sinica Vol. 45, Issue 10, Pages: 2368-2374(2017)
- 作者机构：
  
  空军工程大学防空反导学院,陕西,西安,710051
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61273275)
- DOI：10.3969/j.issn.0372-2112.2017.10.009
  CLC： TP751.1
- Published Online：25 October 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
TANG Yi-dong, HUANG Shu-cai, XUE Ai-jun. Sparse Representation Based Band Selection for Hyperspectral Imagery Target Detection[J]. Acta Electronica Sinica, 2017, 45(10): 2368-2374.
DOI：

TANG Yi-dong, HUANG Shu-cai, XUE Ai-jun. Sparse Representation Based Band Selection for Hyperspectral Imagery Target Detection[J]. Acta Electronica Sinica, 2017, 45(10): 2368-2374. DOI： 10.3969/j.issn.0372-2112.2017.10.009.

摘要

随着高光谱成像技术的发展，日益提高的光谱分辨率在提高目标检测和识别能力的同时，其较高的数据维度和较大的数据量也为数据分析和处理带来了很大的挑战.波段选择作为一种有效提高处理效率的技术受到广泛关注，但却鲜有专门针对目标检测设计的方法.针对上述问题，本文在分析约束能量最小化（CEM）检测算法特点的基础上，提出了一种面向目标检测，基于稀疏表示的波段选择方法.该方法首先基于数据的对称KL散度分布情况，将原始高光谱数据划分为若干波段子空间.然后在各子空间内稀疏重构检测结果，利用选择波段与稀疏向量非零项的一一对应关系，通过求解最优化问题实现波段选择.实验结果验证了该方法的有效性.

Abstract

With the development of hyperspectral imaging technology

the raising spectral resolution improves the ability of target detection and classification.But its great data size and high data dimension also bring challenge to analysis and processing.As a dimensionality reduction technology

band selection (BS) plays an important role in the pre-processing of hyperspectral imagery (HSI).However

few BS algorithms are specially designed for target detection.In this paper

based on analyzing the character of constrained energy minimization (CEM) algorithm

a sparse representation based band selection method (TD-SRBBS) is proposed for HSI target detection.The symmetric Kullback-Leibler divergence is defined for subspatial partition

which makes the original HSI dataset some subset.Sparse reconstruct the detection result in each subset

and then band selection can be implemented based on the one-to-one correspondence between selected bands and nonzero elements of sparse vector.The experiments on real hyperspectral data demonstrate the effectiveness of TD-SRBBS.

关键词

Keywords

references

Views

278

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Target Detection in Hyperspectral Imagery Based on Linear Mixing Model Reconstructed from Measurements

Collaborative Representation-Based Binary Hypothesis Model for Hyperspectral Target Detection

Cross-Modal SAR Target Detection via Progressive Knowledge Transfer

A Spatiotemporal Fusion Algorithm of Remote Sensing Images Based on Cross-Scale Similarity Prior

Related Author

HE Lin

PAN Quan

DI Wei

LI Yuan-qing

HE Lin

PAN Quan

ZHAO Yong-qiang

LING Qiang

Related Institution

College of Automation Science and Engineering,South China University of Technology

College of Automation, Northwestern Polytechnical University

School of Civil Engineering,Purdue University,West Lafayette

College of Automation Science and EngineeringSouth China University of TechnologyGuangzhouGuangdong 510641China

College of AutomationNorthwestern Polytechnical UniversityXi’anShaanxi 710072China

⁰